OpenHuman v0.58.7

The Meetings & Connections Power‑Up

v0.58.0–v0.58.7 is packed with a sharper Meetings experience, faster + more reliable Connections (Skills/MCP), and a big wave of stability upgrades across agents, memory, and providers. 🚀

Highlights

Meetings, end-to-end polish 🎥

Meetings got a full redesign with a platform selector, a clean history master-detail layout, and smarter defaults—plus a bunch of quality fixes that make sessions feel more “alive” and less error-prone. You’ll see better UI feedback (including “Leaving…” states), automatic refresh of Recent Calls when a meeting ends, and improved handling of backend capacity messaging.

Wake phrases are now correctly forwarded for active meeting bots, meeting display names can auto-fill from your connected account, and the auto-summarize policy is honored—with a new manual summary RPC for “Ask” flows.
(#4308, #4348, #4347, #4221, #4231, #4297, #4353) — Thank you @graycyrus and @YOMXXX!

Connections: MCP & Skills that feel fast (and stay fast) 🔌

MCP took a major leap forward: the MCP Servers page is now “complete” with a curated catalog, lifecycle improvements, and E2E coverage. Under the hood, MCP tool calls return as soon as the reply frame arrives (huge latency win), stdio servers spawn with the user’s real shell PATH (hello npx/uvx), and schema migrations are now concurrency-safe.

Auth and install UX also improved across the board: clearer MCP 401 explanations (with safer messaging), better “installed / installing” card state, and Skills improvements like activation persistence, registry caching + pagination, and latency instrumentation.
(#4300, #4220, #4295, #4219, #4321, #4224, #4288, #4120, #4182, #4188, #4238) — Thank you @YellowSnnowmann, @M3gA-Mind, @oxoxDev, and @YOMXXX!

Chat experience: attachments, visuals, and smoother long turns 💬

Chat now has a first-class attachment button for images, videos, and documents—with drag-and-drop and paste support. Code blocks gained syntax highlighting across markdown surfaces, and the composer/footer layout now dynamically reserves space so queued follow-ups (and other expanding footer content) no longer overlap the conversation.

On the reliability side, long reasoning turns stay alive past the old 2-minute silence timeout thanks to a heartbeat progress signal.
(#4292, #4335, #4334, #4282) — Thank you @oxoxDev and @graycyrus!

Agents & tool runtime: fewer loops, clearer stops 🧠

Agent orchestration is now much harder to derail: identical tool-call loops are detected and halted, stuck sub-agents can return as explicitly incomplete, and session tool calls now respect timeouts instead of hanging forever. The MCP Setup Agent no longer gets trapped in a re-spawn loop when pausing for user clarification, and goal completion instructions were strengthened to improve auto-complete behavior.

The built-in researcher agent was also tightened up with a bounded tool surface and capped per-turn output.
(#4230, #4262, #4303, #4310, #4313, #4314) — Thank you @sanil-23, @YOMXXX, @oxoxDev, @salarkhannn, and @senamakel!

Memory & intelligence: better continuity and safer cross-host behavior 🗂️

Memory got meaningful durability upgrades: summary-only wiki history is now tracked via git, cross-thread search is faster by ranking before cloning heavy hits, and the Trees UI has clearer feedback and a stable toolbar layout even when vault guidance opens.

For multi-device setups, cross-host vault paths are now explicitly surfaced as belonging to a particular host OS—so a frontend won’t try to open macOS paths on Linux (or vice versa). The Brain memory graph reliably reloads after re-login, and the Intelligence page scrolls correctly inside the Brain card.
(#4168, #4311, #4331, #4342, #4330, #4223, #4332) — Thank you @senamakel, @mysma-9403, @graycyrus, @oxoxDev, and @M3gA-Mind!

Provider, inference, and observability hardening 🧰

This release includes a broad set of fixes that turn noisy “errors” into correctly-classified expected states, reduce retry storms, and improve resilience across providers and local environments. Highlights include: safer model-catalog parsing, better embeddings verification (including auto-detected dimensions and Gemini model-id normalization), improved handling of quota/limit states, and more robust OpenAI-compat parsing.

Backend routing is also safer: backend API calls won’t accidentally route to a BYO cloud inference host. For channels, OAuth “Connecting” states now recover cleanly when deep-link roundtrips fail. And for cron jobs, missing API keys halt early (with better user-visible error surfacing).
(#4157, #4160, #4184, #4186, #4185, #4207, #4209, #4210, #4161, #4189, #4187, #4208, #4286, #4306, #4166, #4169) — Thank you @oxoxDev and @M3gA-Mind!

Tiny Place: identity + trading fixes, smoother Linux rendering 🪙

Tiny Place saw a strong round of fixes: correct pricing tiers, USDC SPL mint acceptance for handle registration, longer RPC timeouts for bounty creation, and a more polished UX for destructive actions via an in-app confirm modal. Trading is more usable too—balances are read from the correct settlement RPC, Buy re-enables properly after a purchase attempt, and users can switch their primary handle across multiple identities.

On Linux, the world renderer now gets a working WebGL context via SwiftShader (without reverting to the old “disable GPU” blunt instrument).
(#4215, #4211, #4212, #4214, #4218, #4217, #4216, #4213) — Thank you @M3gA-Mind!

Voice, Human, devices, and desktop reliability 🎙️

Voice on macOS is more robust: in-process Whisper STT can work without relying on an external binary, and the install/test UI behaves more predictably. Human UI also gets a practical fix: the mic device selector stays within the viewport instead of clipping off-screen.

Desktop reliability improvements include a CEF GPU-disable startup override for tough environments, Debian installs preferring .deb packages (with proper runtime deps), and device pairing now using the correct Socket.IO ACK flow.
(#3915, #4343, #4309, #4263, #4355) — Thank you @YellowSnnowmann, @graycyrus, @sam, and @YOMXXX!

New creative tools, mascots, and model routing ✨

There’s a whole new media-generation domain with image/video agents and GMI media tools that download outputs into stable local paths. Mascots can now load from a GitHub-backed manifest, making it easier to expand and evolve the Human experience over time. ...

OpenHuman v0.58.0

Super Context is Here! 🎉

v0.57.53 to v0.58.0 brings 124 PRs across 133 commits, with upgrades across memory, voice, agents, reliability, and developer foundations. Thank you to everyone who contributed to this release. ✨

Highlights 🚀

🧠 Memory & intelligence

Memory and intelligence flows are faster, clearer, and more resilient, from source sync controls and richer ingest to batched embeddings and delegated memory retrieval. (#3947, #3948, #3949, #3951, #3959, #3960, #3999, #4008, #4049, #4051, #4054, #4063, #4066, #4067, #4070, #4083, #4086, #4087, #4100, #4106, #4107, #4133, #4138) — Thank you @senamakel, @M3gA-Mind, @oxoxDev, @graycyrus, @mysma-9403, @Subharup-31, @sanil-23, and @senamakel-droid!

✅ Tasks, chat & agent workflows

Task, chat, and agent workflows become easier to steer and inspect, with better task boards, persistent run state, safer delegation, and clearer model/thread controls. (#3918, #3925, #3933, #3965, #3966, #3970, #3977, #3978, #3983, #3985, #3987, #3990, #3994, #4003, #4007, #4011, #4012, #4016, #4017, #4018, #4019, #4021, #4027, #4030, #4031, #4050, #4060, #4061, #4062, #4080, #4081, #4082, #4084, #4085, #4102, #4103, #4105, #4114, #4128, #4129, #4130, #4132, #4134, #4136, #4139, #4141, #4156, #4173) — Thank you @Felyx-Fu, @graycyrus, @sanil-23, @M3gA-Mind, @nazarli-shabnam, @ly-wang19, @YellowSnnowmann, @oxoxDev, @senamakel, @hgunduzoglu, and @senamakel-droid!

🔐 Reliability, security & platform polish

Reliability and platform behavior are tightened across security policy, credential handling, session health, CEF startup, Windows filesystem edge cases, and release-only build paths. (#3958, #3969, #3974, #3976, #3992, #4004, #4009, #4028, #4058, #4064, #4065, #4068, #4069, #4076, #4078, #4101) — Thank you @M3gA-Mind, @oxoxDev, and @senamakel!

🧩 Integrations, UI & developer foundations

Integrations, UI polish, and developer foundations also move forward, including clearer connected-account surfaces, meeting-agent wiring, presentation/artifact improvements, and cleaner docs/code organization. (#3718, #3941, #3946, #3973, #3975, #3981, #3982, #3984, #3986, #3988, #3989, #3995, #3998, #4002, #4026, #4032, #4037, #4052, #4053, #4057, #4071, #4072, #4079, #4108, #4109, #4110, #4113, #4115, #4123, #4124, #4125, #4126, #4127, #4131, #4137, #4162, #4171) — Thank you @obchain, @martian56, @M3gA-Mind, @nazarli-shabnam, @graycyrus, @senamakel, @oxoxDev, @sanil-23, @YellowSnnowmann, and @senamakel-droid!

New Contributors 🌟

• Welcome Martian! Thank you for #3941 fix(composio): pin toolkit_versions=latest in direct-mode tool listings (#3932); #3946 fix(tauri): identify foreign process on core port + consent-gated force-quit (#3331).
• Welcome Shabnam! Thank you for #3970 fix(sentry): re-register inboundFiltersIntegration so ignoreErrors runs; #3984 fix(settings): render Managed provider as always-on badge, not a locked toggle.

Hope y...

OpenHuman v0.57.53

The Stability & Flow Upgrade

This release is packed with quality-of-life polish and reliability fixes across chat, voice, auth, and integrations—plus a few big building blocks for the agent runtime. Enjoy the smoother ride 🎉

Highlights

Chat experience & UI polish ✨

Chat gets a noticeably cleaner feel: scheduled morning briefings now stay grouped (headings + bodies in the same bubble), approval prompts are easier to read with an opaque warning surface, and GFM markdown tables render correctly in agent output. We also fixed edge-case UI issues like the sidebar composer footer being reachable even on short windows, and improved attachment fallback parsing so FILE markers don’t leak into reconstructed messages.
(#3851, #3790, #3857, #3863, #3795) — Thank you @sanil-23, @discolotus, @YOMXXX, @hgunduzoglu, and @rsd-darshan!

Voice & audio reliability 🎙️

Voice setup and hands-free flows are sturdier: push-to-talk commands are properly allowlisted again, local Whisper/Piper providers can’t be enabled until installation is truly complete (with polling + better progress states), and lapsed-session TTS 401s are now correctly treated as session expiry instead of noisy hard errors.
(#3842, #3861, #3750) — Thank you @oxoxDev and @YOMXXX!

Auth, sessions, and fewer dead-ends 🔐

Sign-in and session handling got smarter: transient /auth/me hiccups no longer prevent session persistence, legacy /auth web callbacks are accepted and rewritten safely for HashRouter, and OpenRouter OAuth now uses the loopback listener’s actual bound port (fixing the “port 3000 busy” case). Multiple 401 paths (integrations + voice) now drive the user into a clean re-login flow instead of failing silently.
(#3746, #3800, #3904, #3749) — Thank you @samrusani, @NgoQuocViet2001, @ly-wang19, and @oxoxDev!

Providers, inference & routing upgrades ⚡

A bunch of provider-facing improvements landed: OpenAI-compatible HTTP timeouts are now configurable (so long reasoning turns don’t get chopped), Gemini tool-call history correctly preserves thought_signature, and user-misconfig errors like /models 404s now get classified at the source with actionable hints. We also added new provider options—ModelScope as a built-in hosted provider, and OMLX as a named local provider with endpoint+key credentials.
(#3864, #3770, #3769, #3773, #3862) — Thank you @hgunduzoglu, @oxoxDev, @yrk111222, and @hliebscher!

Agents: orchestration, subagents, and context headroom 🤖

The agent runtime got major upgrades: an event-driven subconscious trigger pipeline introduces a long-lived orchestrator session, tool-output compaction reduces context bloat (with reversible recovery), and subagents are now async + reusable by default (with lifecycle tools). We also improved failure behavior—agent cascades now stop on the first permanent inference failure with a clearer root cause, and local-context overflow errors are caught pre-dispatch with concrete guidance.
(#3650, #3869, #3887, #3779, #3771) — Thank you @senamakel, @sanil-23, and @oxoxDev!

Memory & sync performance (and correctness) 🧠

Memory got both faster and more correct: semantic recall is query-sensitive again, episodic relevance avoids an O(n²) hot path, and chunk scoring dedup now uses cheaper HashSets. The memory tree sealing path is more concurrent, and source sync (GitHub) and calendar fan-out use bounded concurrency for better throughput. On the sync side, Composio incremental sync is now centralized behind a generic orchestrator (with providers migrated across Notion/GitHub/Linear/ClickUp/Gmail/Slack and cap math moved into a single source of truth).
(#3608, #3782, #3638, #3416, #3434, #3472, #3852, #3860, #3873, #3874, #3924, #3937) — Thank you @michaelk1957, @mysma-9403, and @sanil-23!

Skills, toolchains, and Windows/Linux shell quality 🧰

Skills management is sharper: uninstalling a skill mid-session now retracts it from the live catalog, built-in catalog entries correctly show as Installed, and community skill downloads now resolve via each entry’s sourceUrl (with clearer failure for portal-only sources). On Windows, you can optionally suppress console window flashes when spawning shell commands; on Linux, AppImage builds now sanitize absolute RPATHs and hard-guard bundling of libxdo to prevent launch-time crashes.
(#3745, #3656, #3844, #3747, #3776) — Thank you @obchain, @YonganZhang, and @oxoxDev!

Notifications, cron, billing, and “expected error” hygiene 🧾

Cron and billing paths now behave more sanely: scheduled jobs won’t post failed/empty runs into chat, morning-brief task fetch is scoped to a 24h recency window (extended to Todoist, with fixed stale slugs), and credit prompts are properly gated per selected chat-mode tier (so BYO users don’t get “buy credits” nudges incorrectly). A lot of Sentry noise was also reduced by correctly classifying expected user-state events (billing-state cron floods, disk-full floods, provider exhaustion transient aggregates, OpenAI OAuth token_expired, and credential context preservation).
(#3789, #3872, #3923, #3775, #3913, #3911, #3663, #3803, #3674) — Thank you @sanil-23, @oxoxDev, @Zhang, and @CodeGhost21!

Agent World & Tiny Place expansion 🌍

Agent World continues to grow: TinyPlace now has a dedicated World page with the Pixi city renderer and more reads routed through GraphQL to reduce fan-out. There’s also a curated, agent-friendly TinyPlace tool surface plus a dedicated tinyplace specialist subagent, improved feed sorting, and clearer messaging UX when encrypted DM setup isn’t complete.
(#3867, #3879, #3876, #3868, #3919) — Thank you @senamakel and @Felyx-Fu!

Desktop navigation, feedback, channels, and onboarding 🧭

Navigation and core UX got tuned up: chat threads now have stable /chat/:threadId routes and provider webviews are decoupled from thread routing; onboarding walkthrough targets were updated for the modern UI; and a full in-app Feedback board landed (now presented as “Share Feedback” in a tidy sidebar footer). We also fixed Discord & Telegram messaging end-to-end on desktop, plus small but important UI correctness fixes like routine “Next run” labels near the hour boundary and “Clear App Data” scoping to the active user only.
(#3896, #3944, #3834, #3945, #3794, #3758) — Thank you @senamakel, @YellowSnnowmann, and @obchain!

Internationalization & compatibility fixes 🌐

i18n got a solid round of love: the memory Sync Audit panel is now fully localized, AI routing workload labels/descriptions/hints are localized (with full German coverage), and placeholder substitution bugs like {providerName} rendering literally are fixed across multiple surfaces. We also improved legacy compatibility: older ...

OpenHuman v0.57.52

The Agent World & Wallet Safety Upgrade

This release brings a big leap in Agent World depth, smoother navigation across the app, and a major wallet-safety fix—plus quality-of-life polish throughout. 🎉

Highlights

Agent World goes native 🌍

Agent World (tiny.place) is now deeply integrated with a full Rust data layer and a ported React UI, unlocking core surfaces like Feed, Messages, Jobs/Bounties, Directory/Identities, and devnet payment flows with confirm-before-spend. On top of that foundation, Explore now pulls real live data, identity registration publishes to the Directory correctly, DMs resolve handles reliably, and groups/creating bounties give clearer UX feedback.
(#3780, #3839, #3847, #3846, #3840, #3837, #3835) — Thank you @graycyrus!

Smarter agent workflows & orchestration 🤖

Detached background sub-agents now cleanly cancel when their parent thread is closed, preventing “fire-and-forget” runs against deleted conversations. And the agent is now grounded to a live per-turn clock so time-relative statements (“good morning”, “today/tomorrow”) stay accurate across long sessions.
(#3742, #3752) — Thank you @sanil-23!

Wallet safety, visibility, and trust 🔐

A critical wallet fix ensures the Recovery Phrase experience reveals the existing phrase instead of accidentally regenerating/overwriting a user’s wallet—now guarded by an explicit “force” path and a clearer UI state machine. Wallet access is also more discoverable with a prominent sidebar entry, and Agent World now shows a handy wallet address chip in its sidebar header.
(#3849, #3836, #3838) — Thank you @graycyrus!

Navigation & chat shell polish 🧭

The shell is easier to use when collapsed thanks to an icon-only navigation rail that stays fully navigable, complete with tooltips and active state. The sidebar header is also cleaner (language picker moved to Settings), and the chat/sidebar experience gets a meaningful rework with thread-title rename flowing into the sidebar and other chat shell refinements.
(#3802, #3810, #3854) — Thank you @graycyrus and @senamakel!

Rewards + Discord linking made real 🎁

Discord linking now actually runs OAuth from the Rewards page (and returns you right back), and the Rewards experience adds disconnect/re-link plus clear per-achievement role assignment status—so claiming roles is transparent and actionable.
(#3748, #3766) — Thank you @YellowSnnowmann!

Localization & UX correctness fixes 🌐

More user-facing strings are now fully localized, including OpenHuman Link account/notification messaging and the Model Council hint picker labels—closing gaps where English literals bypassed i18n. Also, Conscious loop triggers are now guarded to prevent duplicate runs on rapid clicks.
(#3702, #3704, #3708) — Thank you @obchain!

Embedded webview providers expand 🧩

The embedded webview account picker now supports more mainstream providers—Gmail, Outlook, Instagram, and X—across frontend, Tauri shell, core login detection, and provider recipes.
(#3755) — Thank you @senamakel!

Test & release health improvements 🧪

E2E coverage and Playwright/Vitest setup were adapted to the chat-as-home shell, fixing navigation races and stabilizing coverage timeouts.
(#3754) — Thank you @senamakel!

Agent World UI alignment & sidebar cleanup 🧹

Agent World continues to be streamlined: Jobs is now hidden from the Agent World sidebar (while keeping the route accessible for deep links), and job applying gains an agent tool plus a clearer “proposal submitted” success UX.
(#3855, #3848) — Thank you @graycyrus!

Linux packaging reliability 🐧

AppImage bundling now consistently replaces the bundled ld-linux from the CI host system to prevent glibc mismatch crashes seen on newer distros (e.g., Fedora with glibc ≥ 2.42).
(#3645) — Thank you @0xhis!

New Contributors

• Thank you @0xhis for fixing AppImage glibc mismatch crashes by ensuring the bundled ld-linux is always replaced from the host system. (#3645)

Hope you’ll join our Discord—come grab your exclusive roles and contributor rewards!

Contributor Credits

Huge thanks to everyone who shipped this release: @0xhis, @graycyrus, @obchain, @sanil-23, @senamakel, @YellowSnnowmann, and our ever-helpful automation friend @github-actions[bot].

Full Compare

v0.57.44...v0.57.52

OpenHuman v0.57.44

The Orchestration & Everyday-Flow Upgrade

This release brings a big leap in how OpenHuman runs—from smarter multi-agent orchestration and skills, to a cleaner two-panel app shell, to faster and quieter memory + inference pipelines. 🚀

Highlights

Intelligence & multi-agent orchestration 🧠

OpenHuman’s “intelligence layer” gets much more real: async sub-agents can now be steered while running and awaited cleanly, teammate agents can actually execute tasks end-to-end (with messaging captured in timelines), and durable workflow orchestration now has a first-class UI with an approval gate for high-cost runs. Worktree isolation is also wired through RPC + UI so complex runs can stay contained and observable.

(#3641, #3637, #3697, #3696) — Thank you @senamakel and @oxoxDev!

Skills, vision, and better agent grounding 🧰

Skills graduate to a catalog-driven run_skill flow with an isolated executor and mid-session refresh—making skill runs more reliable and less invasive to chat history. There’s also a new vision-v1 tier plus a dedicated vision sub-agent for image understanding, and tighter numeric grounding rules to keep numbers copied exactly from observed sources.

(#3722, #3699, #3678) — Thank you @sanil-23 and @sam!

Chat & background work UX polish 💬

Detached sub-agents now have a proper “Background tasks” panel and deliver results back into chat in an idle-gated, batched way—so you don’t get interrupted mid-turn. Conversations also get a key rendering fix: task insights now appear once, after the full response. Plus, proactive messages are now limited to fresh threads, and resume-on-reopen errors are classified and threads are “de-poisoned” to recover cleanly.

(#3735, #3726, #3713, #3714) — Thank you @sanil-23!

A new two-panel desktop shell & settings experience 🧭

The desktop app’s layout continues its transformation: TwoPanelLayout becomes the backbone across Settings/Brain/Connections/Chat, settings panels are unified with shared primitives for consistent navigation, and the root shell now adopts a unified sidebar with Chat as the home experience. There’s also a dedicated Desktop Agent setup panel to make permissions, seamless mode, always-on, and wake-word setup feel centralized and clear.

(#3643, #3646, #3751, #3634) — Thank you @senamakel and @M3gA-Mind!

MCP, connectors, and provider setup—faster and more actionable 🔌

MCP servers are now usable end-to-end by the agent (including OAuth flows and an agent bridge), boot is faster thanks to concurrent server spawning, and 401s are surfaced as an actionable “needs sign-in” state. Claude Code becomes an opt-in provider with a macOS auth fix and OpenHuman memory over MCP, and Composio/memory-source reconciliation is significantly more efficient. A small but helpful settings addition also adds a “Get API key” link for Kimi.

(#3648, #3429, #3719, #3647, #3432, #3685) — Thank you @sanil-23, @mysma-9403, and @Huyuochi!

Memory & retrieval that feels more “right” 🧠

Memory status reporting is smarter (only unrecoverable failures show as “error,” and the degraded latch clears on any completed extraction). There’s a new RPC to fully delete a memory source by exact source_id, and a new cover_window retrieval mode that powers a more relevant “last 24h” morning brief. Under the hood, extraction scoring avoids unnecessary cloning for lower overhead.

(#3630, #3631, #3664, #3700, #3436) — Thank you @sanil-23, @michaelk1957, and @mysma-9403!

Inference, embeddings, and observability hardening 🛡️

This range focuses heavily on making the app quieter, safer, and more resilient: OAuth requests now use a Codex-compatible client version; Responses API role/kind mismatches are fixed; extraction now caps max_tokens and correctly treats provider 402s as non-retryable to stop storms. Embeddings get multiple guardrails (refuse empty inputs, block chat-only custom endpoints with no embeddings API, and prevent LM Studio “no models loaded” floods). BYO provider 401/403 auth failures are demoted from Sentry, SQLite “disk full” noise is filtered, and model test failures are properly classified.

(#3414, #3626, #3617, #3670, #3629, #3688, #3689, #3672, #3676) — Thank you @Junwon, @oxoxDev, @CodeGhost21, @obchain, and @Zhang!

Meetings & voice in the real world 🗣️

Meetings level up in multiple directions: the Meet bot can now participate in-call (streaming, approvals, active vs listen-only), Recent Calls is populated correctly for the backend meet flow, and after-call summaries + context labels make threads immediately scannable. Calendar-triggered prompts and a Meeting Assistant settings UI help you join at the right time. Telegram bots also now accept inbound voice messages and transcribe them before dispatching to the agent.

(#3677, #3710, #3709, #3721, #3679) — Thank you @YellowSnnowmann and @ron Liu!

Security, stability, and test coverage ✅

A major hardening audit pass tightens core RPC auth, deep-link CSRF protections, inference resilience, and secrets handling—with regression tests included. Agent harness behavior now has robust Rust + browser E2E coverage (plus docs updates), the desktop Appium suite is repaired after the IA refactors, and observability regressions are explicitly tested for known transient shapes. There’s also a deps bump in the Postgres stack to clear recent RUSTSEC advisories.

(#3652, #3665, #3666, #3667, #3669, #3668, #3649, #3658, #3659, #3660, #3661, #3662, #3690) — Thank you @senamakel, @YellowSnnowmann, @Zhang, and @obchain!

Core plumbing & compatibility improvements ⚙️

Under-the-hood changes improve compatibility and reduce surprises: CDP scanners are migrated to an in-process transport (dropping the TCP DevTools port), Notion markdown fetch is now bounded-concurrent, managed-tool budget probing is cached behind a short TTL, subagents can auto-compact summarize when context fills, scheduler routing is scoped to avoid misroutes for calendar/meet-link reads, legacy health RPC names now alias to health_snapshot, and unknown-method probe traffic no longer pages Sentry. Login troubleshooting also improves by surfacing a previously silent /auth/me store failure.

(#3636, #3433, #3431, #3694, #3731, #3743, #3744, #3734) — Thank you @oxoxDev and @sanil-23!

Cloud/marketplace integration (opt-in) ☁️

An opt-in AgentBox adapter adds marketplace-style /run + job polling endpoints and can auto-register a GMI OpenAI-compatible provider at startup—kept fully off by default to avoid impacting desktop builds.

(#3651) — Thank you @CodeGhost21!

Additional...

OpenHuman v0.57.40

The Parallel Power Upgrade

This release brings a faster, more transparent desktop experience—more concurrency in chat, smoother reliability in memory flows, and easier access to diagnostics. 🚀

Highlights

Faster chat, more parallelism ⚡

Agent inference now runs concurrently instead of one-at-a-time—both across threads (no more single global active-thread lock) and within a thread via parallel “forked” turns. Cancellation is also hardened to be more cooperative and resilient under load. (#3633) — Thank you @senamakel!

Memory source reliability improvements 🧠

Memory sources now re-fetch when a session becomes authenticated, improving consistency and reducing flakiness in memory-source UI flows after reloads. This also adds test coverage to lock in the behavior. (#3621) — Thank you @sanil-23!

Smoother CI + test stability 🧪

CI and tests got a cleanup pass to eliminate multiple flaky/failing categories: removing stale UI assertions, fixing async race conditions in autosave/memory, and adjusting Playwright timeouts to reduce infrastructure flakes. Also includes a small UX regression fix where a join success toast could fail to fire due to an unmounting effect. (#3618, #3623) — Thank you @senamakel-droid and @sanil-23!

Always-on Developer & Diagnostics access 🛠️

Developer & Diagnostics settings are now always visible—no more “Developer Mode” gate. This surfaces the Settings section, related settings search entries, and the Intelligence “council” tab by default, with tests updated accordingly. (#3639) — Thank you @senamakel!

Contributor Credits

Thanks to everyone who contributed to this release: @github-actions[bot], @sanil-23, @senamakel, and @senamakel-droid.

Full Compare

v0.57.39...v0.57.40

OpenHuman v0.57.39

The Intelligence Upgrade 🎉

v0.57.18 to v0.57.39 brings 125 PRs across 146 commits, with upgrades across memory, voice, agents, reliability, and developer foundations. Thank you to everyone who contributed to this release. ✨

Highlights 🚀

🎙️ Voice & hands-free control

Voice and hands-free control get more useful across the desktop, with always-on listening, global push-to-talk, faster command routing, and stronger automation paths for interacting with apps. (#3349, #3420, #3531, #3545, #3551, #3558, #3619) — Thank you @CodeGhost21, @sanil-23, @M3gA-Mind, and @oxoxDev!

🧠 Memory & intelligence

Memory and intelligence flows are faster, clearer, and more resilient, from source sync controls and richer ingest to batched embeddings and delegated memory retrieval. (#3413, #3417, #3418, #3421, #3422, #3424, #3428, #3438, #3439, #3441, #3444, #3446, #3447, #3454, #3459, #3479, #3480, #3499, #3521, #3578, #3580, #3583, #3586, #3587, #3590, #3598, #3611, #3613) — Thank you @sanil-23, @senamakel, @senamakel-droid, @oxoxDev, @graycyrus, and @michaelk1957!

✅ Tasks, chat & agent workflows

Task, chat, and agent workflows become easier to steer and inspect, with better task boards, persistent run state, safer delegation, and clearer model/thread controls. (#3388, #3399, #3411, #3412, #3419, #3426, #3443, #3456, #3457, #3458, #3477, #3481, #3483, #3497, #3500, #3519, #3528, #3530, #3532, #3533, #3544, #3546, #3553, #3555, #3556, #3562, #3563, #3564, #3581, #3584, #3591, #3594, #3596, #3597, #3600, #3601, #3607, #3610) — Thank you @senamakel, @graycyrus, @sanil-23, @senamakel-droid, @oxoxDev, @alexzhu0, and @YellowSnnowmann!

🔐 Reliability, security & platform polish

Reliability and platform behavior are tightened across security policy, credential handling, session health, CEF startup, Windows filesystem edge cases, and release-only build paths. (#3409, #3423, #3427, #3450, #3496, #3498, #3526, #3529, #3534, #3557, #3559, #3579, #3589) — Thank you @oxoxDev, @senamakel, @M3gA-Mind, and @sanil-23!

🧩 Integrations, UI & developer foundations

Integrations, UI polish, and developer foundations also move forward, including clearer connected-account surfaces, meeting-agent wiring, presentation/artifact improvements, and cleaner docs/code organization. (#3402, #3442, #3445, #3448, #3451, #3452, #3453, #3455, #3460, #3461, #3462, #3473, #3476, #3485, #3492, #3501, #3502, #3515, #3516, #3517, #3518, #3520, #3527, #3536, #3543, #3552, #3569, #3571, #3572, #3573, #3574, #3575, #3582, #3588, #3592, #3593, #3599, #3612, #3614) — Thank you @oxoxDev, @senamakel-droid, @senamakel, @YellowSnnowmann, @Sathvik-1007, @graycyrus, @sanil-23, and @alexzhu0!

New Contributors 🌟

• Welcome michaelk1957! Thank you for #3598 fix(memory): stop oversized/dense chunks from breaking bge-m3 embedding.

Hope you join the Discord for exclusive roles and contributor rewards!

Contributor Credits 🙌

• Alexzhu (#3536, #3543, #3544) — thank you!
• CodeGhost21 (#3349) — thank you!
• Cyrus Gray (#3399, #3518, #3533, #3569, #3573, ...

OpenHuman v0.57.18

What's Changed

• feat(orchestrator): wire generate_presentation + require grounding (#2780) by @oxoxDev in #3029
• fix(inference): stream + SSE-aggregate Codex OAuth Responses calls (#3201) by @YOMXXX in #3288
• Add task source UI and agent launch flow by @senamakel in #3279
• perf(memory_sync): bounded-concurrency GitHub item reads by @mysma-9403 in #3287
• feat(artifacts): publish ArtifactPending event + artifact_pending socket bridge (#3162 backend) by @YOMXXX in #3277
• feat(file_state): guard cross-agent file edits from stale sibling writes by @senamakel in #3316
• feat(agent): add active-run steering and queue controls by @senamakel in #3317
• fix(chat): rename default thread label to general by @senamakel in #3319
• Suggest OpenRouter free models when credits run out by @senamakel in #3320
• feat(agent): persist oversized tool outputs by @senamakel-droid in #3327
• Bucket chat threads by source by @senamakel in #3330
• feat(chat): Quick/Reasoning toggle + resolved model display by @senamakel in #3325
• feat(tasks): autonomously execute approved/assigned task-board work (poller + update_task + repetition fix) by @sanil-23 in #3326
• feat(tools/system): route node_exec and npm_exec through sandbox backend like shell by @CodeGhost21 in #3309
• feat(artifacts): persist thread_id + ai_list_artifacts thread filter (#3226) by @YOMXXX in #3274
• feat(memory-sync): record periodic Composio syncs in the cost audit (#3111 follow-up) by @justinhsu1477 in #3276
• fix(composio): correct direct-mode v3 execute contract + classify 404/410 as action-not-found (#3219) by @oxoxDev in #3298
• feat(presentation): embed images in generated decks (#3209) by @oxoxDev in #3299
• docs(config): refer to minimax/m3 in team model-pin example by @octo-patch in #3303
• perf(memory_sync): bounded-concurrency Notion/ClickUp/Linear ingest by @mysma-9403 in #3322
• fix(composio): expose daily-budget + sync-interval via env (#2437 F) by @CodeGhost21 in #3314
• feat(settings): make action_dir editable in Agent OS access (#3240) by @oxoxDev in #3305
• feat(computer): main-thread synthetic-input executor + CEF crash fix (1/8 of #3307) by @M3gA-Mind in #3340
• feat: tighten runtime policy + transport guards v3 by @oxoxDev in #3306
• feat(agent): add active-run steering and queue controls by @senamakel in #3270
• fix(cron): halt agent-job retry on backend session-expired (TAURI-RUST-N) by @CodeGhost21 in #3350
• feat(accessibility): AX/UIA perception + automate engine (2/8 of #3307) by @M3gA-Mind in #3341
• fix(onboarding): brand logo on welcome + back-to-welcome from first step by @M3gA-Mind in #3366
• fix(inference,ai-settings): prevent + handle ollama embedding-model-as-chat (Sentry TAURI-RUST-4P6) (#3359) by @oxoxDev in #3360
• fix(intelligence): deduplicate and label connections in integration source picker by @YellowSnnowmann in #3361
• feat(agent): wire automate/ax_interact computer tools (3/8 of #3307) by @M3gA-Mind in #3342
• fix(cron): emit poll-tick health recovery so a single failed job can't permanently brick the scheduler (#3312) by @YOMXXX in #3329
• feat(agent): reduce orchestrator prompt bloat by @senamakel in #3367
• feat(voice): Phase 2 always-on listening engine + RPC (4/8 of #3307) by @M3gA-Mind in #3343
• fix(memory): thread BYO embedding credential — stop Cohere empty-key 401 flood (#3354) by @oxoxDev in #3358
• fix(credentials): retry transient Windows FS errors when persisting auth-profiles.json (#3355) by @oxoxDev in #3364
• feat(memory-sources): default sync sources on with conservative caps, per-source settings & All In by @graycyrus in #3304
• feat(settings): make action_dir editable via Settings → Agent access by @CodeGhost21 in #3313
• Implement SQLite-backed mtime state store by @manucian-official in #3186
• feat(voice): always-on Settings toggle + debug panel + i18n (5/8 of #3307) by @M3gA-Mind in #3344
• feat(notch): always-visible macOS notch status pill (6/8 of #3307) by @M3gA-Mind in #3345
• fix(credentials): reject expired session locally + gate usage polling — RCA for backend 401 flood (#3297) by @oxoxDev in #3384
• feat(agent): add control specialists and async subagent spawning by @senamakel in #3379
• feat(voice): Phase 3 fast command router (7/8 of #3307) by @M3gA-Mind in #3346
• feat(monitor): add first-class background monitor module by @senamakel in #3382
• feat(agent): expose agent library surface by @senamakel in #3383
• feat(memory): Notion doc-aware versioned memory tree + page-content ingest by @sanil-23 in #3378
• feat(accessibility): vision-click fallback for Electron/partial-AX apps (8/8 of #3307) by @M3gA-Mind in #3362
• feat(task-board): autonomous task runs as live task sessions (View work, cancel, degeneration guards) by @sanil-23 in #3380
• docs: add Urdu (ur-pk) README translation with RTL support by @AMIK-coorporations in #3387
• feat(mcp): multi-server lifecycle — enable/disable + error visibility (#3196) by @CodeGhost21 in #3339
• fix(keyring): don't mint a new master key on keychain access-denied (#3311) by @oxoxDev in #3338
• Test subagent cache reuse and chat tier routing by @senamakel in #3389
• Persist thread sidebar visibility by @senamakel in #3390
• feat(memory): clean noisy Notion markdown before ingest by @sanil-23 in #3381
• Persist agent run ledger state by @senamakel in #3391
• refactor(workflows): merge skills into the unified workflows primitive by @sanil-23 in #3324
• fix(composio): enrich connection picker with cached account identity (#3356) by @YellowSnnowmann in #3400
• fix(channels): presentation module private in release breaks the build (v0.57.16 release-blocker) by @M3gA-Mind in #3406
• fix(memory-sync): reliable per-source sync indicators and counters by @graycyrus in #3308
• feat(memory-sources): disable non-syncable toolkits in Add Source picker by @graycyrus in #3395
• feat(appearance): add global font size setting (#3120) by @graycyrus in #3396
• feat(intelligence): strip Memory tab to core view, hide analysis sub-pills by @graycyrus in #3397
• Improve council agent UX and persistence by @senamakel in #3393
• perf(memory): batch re-embed backfill into one provider request by @mysma-9403 in #3392
• test(credentials): cover rename-stage retry + best-effort tmp cleanup (#3364 follow-up) by @oxoxDev in #3398
• fix(composio): show connection ID in picker when no identity cached by @YellowSnnowmann in #3405
• fix(inference): stop Codex CLI import user-state errors flooding Sentry (#3403) by @oxoxDev in #3404
• feat(memory-sync): configurable global sync interval (4h/12h/24h/manual) by @graycyrus in #3408
• chore(welcome): remove orphaned useBackendReachable probe (#2037) by @oxoxDev in #3410
• feat(agent_meetings): wire mascotId through full stack + fix tests by @YellowSnnowmann in https://githu...

OpenHuman v0.57.13

What's Changed

• refactor: improve matrix parsing validation and performance by @manucian-official in #3129
• fix(inference/ollama): use prompt-guided tool calling so skills work on Ollama (#3098 sub-issue 3) by @CodeGhost21 in #3229
• feat(memory-tree): per-integration health strip (#2763) by @CodeGhost21 in #3230
• fix(channels/telegram): wire ApprovalGate end-to-end for Telegram turns (#3098 sub-issue 2) by @CodeGhost21 in #3232
• docs(claude.md): document action sandbox vs internal workspace split by @CodeGhost21 in #3241
• test(memory-sync): E2E + Vitest coverage for #3113 sync pipeline (#3116) by @oxoxDev in #3194
• feat(voice): auto-send dictation transcript + allowlist app-launch commands (#3148 Phase 1) by @M3gA-Mind in #3168
• fix(scripts): add short help to GitHub test map by @alexzhu0 in #3223
• fix(scripts): add short help to stale CI cleanup by @alexzhu0 in #3222
• docs: remove stale coverage matrix PR-local markers by @alexzhu0 in #3220
• perf(learning): bounded-concurrency persist in transcript ingestion by @mysma-9403 in #3234
• fix(orchestrator): force code-repo delegation when reading stalls (#3102) by @CodeGhost21 in #3214
• perf(memory_store): batch chunk embeddings in upsert_document by @mysma-9403 in #3213
• fix(inference): actionable error for completion-only model 404 + unmistakable run_code failure (#3193) by @oxoxDev in #3211
• feat(memory): pipeline hardening — typed failures, BYO embeddings, doctor, honest status by @zahica1234 in #3076
• fix(agent_prompts): anchor coding-agent prompts in action_dir, not workspace_dir by @CodeGhost21 in #3242
• test(tools/system): lock in action_dir as the CWD for shell-family tools by @CodeGhost21 in #3243
• fix(shell): Windows pre-CEF cache-lock wait to stop relaunch panic (TAURI-RUST-F) by @oxoxDev in #3210
• feat(mcp): sanitize remote tool descriptions + length caps by @oxoxDev in #3215
• feat(chat): Files in this chat — persistent per-chat artifact panel (#3024) by @oxoxDev in #3026
• feat(backend_meet): integrate with backend gmeet bot via Socket.IO by @senamakel in #3182
• feat(settings): AgentAccessPanel reads live action_dir/workspace_dir via RPC by @CodeGhost21 in #3245
• feat(claude-code): Claude Code CLI provider — Phases 1–5 by @finedesignz in #2472
• feat(security): explicit agent turn origin + fail-closed approval gate + memory provenance by @oxoxDev in #3227
• test(playwright): add functional UI flow coverage by @senamakel in #3257
• feat(sandbox): add real sandbox execution backends for agent tools by @senamakel in #3261
• fix(review): use exec and interactive mode for agent CLI invocations by @senamakel in #3262
• feat(inference): local provider profiles and MLX/generic-local support by @senamakel in #3260
• feat(todos): atomic claim primitive for task-board dispatch by @senamakel in #3258
• feat(session_db): add durable agent session database by @senamakel in #3259
• feat(todos): durable task-run liveness and stale reclaim by @senamakel in #3267
• feat(settings): add UI for sandbox execution backend configuration by @senamakel in #3265
• feat(analytics): track chat browser touchpoints by @senamakel in #3269
• fix(memory): group selector ingests by source scope by @senamakel in #3264
• fix(memory): redact source tag debug identifiers by @senamakel in #3272
• feat(todos): add task scheduler race and invariant tests by @senamakel in #3271
• fix(agent): snap budget-trim past orphaned tool results by @sanil-23 in #3266
• fix(agent): drop removed memory_tree modes from orchestrator prompt by @sanil-23 in #3275
• feat(chat): implement image attachment pipeline, gated off (#3205) by @sanil-23 in #3268
• fix(onboarding,billing): surface completeAndExit errors and suppress near-limit banner for custom providers by @YellowSnnowmann in #3278
• fix(composio): defer on_connection_created sync until onboarding completes by @YellowSnnowmann in #3283
• fix(memory-graph): render large graphs in the SVG fallback without freezing by @sanil-23 in #3291

New Contributors

• @finedesignz made their first contribution in #2472

Full Changelog: v0.57.11...v0.57.13

OpenHuman v0.57.11

What's Changed

• Add vault file-system watcher implementation by @manucian-official in #3183
• fix(subconscious): degrade WAL journal mode to fix Intelligence tab hang on shm-incompatible filesystems by @M3gA-Mind in #3233

Full Changelog: v0.57.10...v0.57.11