feat: add Memanto global memory integration for claude-code skills (#508)#607
Closed
zhangzeyu-ai wants to merge 1 commit into
Closed
feat: add Memanto global memory integration for claude-code skills (#508)#607zhangzeyu-ai wants to merge 1 commit into
zhangzeyu-ai wants to merge 1 commit into
Conversation
📝 WalkthroughWalkthroughAdds a new Memanto memory layer example under ChangesMemanto Memory Layer Example
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 5
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@examples/claudecode-skills-memanto/README.md`:
- Line 20: The README's bash example uses Windows CMD syntax "set
MOORCHEH_API_KEY=sk-xxxxxxx"; update that line (the string "set
MOORCHEH_API_KEY=sk-xxxxxxx") to use POSIX shell syntax "export
MOORCHEH_API_KEY=..." for the bash block, or alternatively document both
variants (show "export MOORCHEH_API_KEY=..." for bash/zsh and "set
MOORCHEH_API_KEY=..." for Windows CMD/PowerShell) so the setup instructions
match the annotated shell.
In `@examples/claudecode-skills-memanto/scripts/memanto_memory.py`:
- Line 43: Update the user-facing initialization guidance in memanto_memory.py:
replace the existing print("Error: not initialized. Run 'memanto init' first.")
message with one that instructs the correct CLI for this example, e.g. mention
running "python scripts/memanto_memory.py init" (or the appropriate invocation
used by this script) so users know to run that exact command to initialize;
locate and update the print statement in memanto_memory.py.
- Line 219: The --confidence arg currently allows any float; add validation at
parse time by replacing p.add_argument("--confidence", type=float, ...) with a
validator function (e.g., def confidence_type(v): try: f=float(v) except: raise
argparse.ArgumentTypeError(...) ; if not 0.0 <= f <= 1.0: raise
argparse.ArgumentTypeError("confidence must be between 0 and 1") ; return f) and
pass type=confidence_type to p.add_argument so parsing fails fast with a clear
error for out-of-range values; reference the p.add_argument("--confidence", ...)
call when making the change.
- Line 136: In cmd_recall, guard the score formatting by safely converting score
to float before building score_str: instead of directly calling float(score) in
score_str, try converting score in a try/except (catch TypeError/ValueError) or
check isinstance(score, (int, float)); on failure or non-numeric values treat it
as None or use a placeholder (e.g., "N/A") and then build score_str accordingly
so non-numeric backend values won't raise exceptions.
In `@examples/claudecode-skills-memanto/SKILL.md`:
- Around line 52-63: The fenced code block containing the example transcript
(the block starting with "# Session 1 — store decisions" and the three shell
lines) is missing a language tag and triggers MD040; update the opening fence
from ``` to ```text (or another appropriate language) so the block is recognized
as plain text and the markdown linter stops flagging it.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: f1ca04f5-078c-44d9-9ed7-45822c25857b
📒 Files selected for processing (4)
examples/claudecode-skills-memanto/README.mdexamples/claudecode-skills-memanto/SKILL.mdexamples/claudecode-skills-memanto/requirements.txtexamples/claudecode-skills-memanto/scripts/memanto_memory.py
| # 2. Get a free API key at https://moorcheh.ai | ||
|
|
||
| # 3. Set the key | ||
| set MOORCHEH_API_KEY=sk-xxxxxxx |
There was a problem hiding this comment.
Fix shell command mismatch in setup instructions.
This block is marked bash, but set MOORCHEH_API_KEY=... is Windows CMD syntax and will fail in bash/zsh. Use export MOORCHEH_API_KEY=... (or document both shells explicitly).
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@examples/claudecode-skills-memanto/README.md` at line 20, The README's bash
example uses Windows CMD syntax "set MOORCHEH_API_KEY=sk-xxxxxxx"; update that
line (the string "set MOORCHEH_API_KEY=sk-xxxxxxx") to use POSIX shell syntax
"export MOORCHEH_API_KEY=..." for the bash block, or alternatively document both
variants (show "export MOORCHEH_API_KEY=..." for bash/zsh and "set
MOORCHEH_API_KEY=..." for Windows CMD/PowerShell) so the setup instructions
match the annotated shell.
|
|
||
| def _load_config(): | ||
| if not CONFIG_FILE.exists(): | ||
| print("Error: not initialized. Run 'memanto init' first.") |
There was a problem hiding this comment.
Correct the init guidance string to match this CLI.
The message says Run 'memanto init' first. but this example uses python scripts/memanto_memory.py init. This mismatch makes recovery harder when config is missing.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@examples/claudecode-skills-memanto/scripts/memanto_memory.py` at line 43,
Update the user-facing initialization guidance in memanto_memory.py: replace the
existing print("Error: not initialized. Run 'memanto init' first.") message with
one that instructs the correct CLI for this example, e.g. mention running
"python scripts/memanto_memory.py init" (or the appropriate invocation used by
this script) so users know to run that exact command to initialize; locate and
update the print statement in memanto_memory.py.
| content = m.get("content", m.get("metadata", {}).get("content", "")) | ||
| mtype = m.get("type", m.get("metadata", {}).get("memory_type", "?")) | ||
| score = m.get("score", m.get("similarity", None)) | ||
| score_str = f" [score: {float(score):.3f}]" if score is not None else "" |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "=== File: examples/claudecode-skills-memanto/scripts/memanto_memory.py (lines 110-170) ==="
nl -ba examples/claudecode-skills-memanto/scripts/memanto_memory.py | sed -n '110,170p'
echo
echo "=== Search: float(score) occurrences ==="
rg -n "float\(score\)" examples/claudecode-skills-memanto/scripts/memanto_memory.py || true
rg -n "score_str|score_val|m\.get\(\"score\"" examples/claudecode-skills-memanto/scripts/memanto_memory.py || true
echo
echo "=== Repo-wide search for float(score) in this example ==="
rg -n "float\(score\)" examples/claudecode-skills-memanto || trueRepository: moorcheh-ai/memanto
Length of output: 215
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "=== File: examples/claudecode-skills-memanto/scripts/memanto_memory.py (lines 110-170) ==="
cat -n examples/claudecode-skills-memanto/scripts/memanto_memory.py | sed -n '110,170p'
echo
echo "=== Search: float(score) occurrences (target file) ==="
rg -n "float\(score\)" examples/claudecode-skills-memanto/scripts/memanto_memory.py || true
echo
echo "=== Search: score formatting vars (target file) ==="
rg -n "score_str|score_val|m\.get\(\"score\"" examples/claudecode-skills-memanto/scripts/memanto_memory.py || true
echo
echo "=== Repo-wide search for float(score) in this example ==="
rg -n "float\(score\)" examples/claudecode-skills-memanto || trueRepository: moorcheh-ai/memanto
Length of output: 3264
Guard score formatting in cmd_recall (line 136) against non-numeric backend values.
float(score) will raise TypeError/ValueError if the backend returns a non-numeric value (even when score is not None). Add a safe conversion fallback before formatting.
Proposed fix
- score = m.get("score", m.get("similarity", None))
- score_str = f" [score: {float(score):.3f}]" if score is not None else ""
+ score = m.get("score", m.get("similarity", None))
+ try:
+ score_val = float(score) if score is not None else None
+ except (TypeError, ValueError):
+ score_val = None
+ score_str = f" [score: {score_val:.3f}]" if score_val is not None else ""🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@examples/claudecode-skills-memanto/scripts/memanto_memory.py` at line 136, In
cmd_recall, guard the score formatting by safely converting score to float
before building score_str: instead of directly calling float(score) in
score_str, try converting score in a try/except (catch TypeError/ValueError) or
check isinstance(score, (int, float)); on failure or non-numeric values treat it
as None or use a placeholder (e.g., "N/A") and then build score_str accordingly
so non-numeric backend values won't raise exceptions.
| p.add_argument("content", help="Memory content") | ||
| p.add_argument("--type", "-t", help="Memory type (auto-detected if omitted)") | ||
| p.add_argument("--tags", nargs="*", default=[], help="Tags") | ||
| p.add_argument("--confidence", type=float, default=0.8, help="Confidence 0–1") |
There was a problem hiding this comment.
Validate --confidence range at parse time.
Help text says 0–1, but values outside that range are currently accepted and passed through. Add argparse validation to fail fast with a clear error.
Proposed fix
+ def _confidence_01(value):
+ v = float(value)
+ if not 0.0 <= v <= 1.0:
+ raise argparse.ArgumentTypeError("confidence must be between 0 and 1")
+ return v
...
- p.add_argument("--confidence", type=float, default=0.8, help="Confidence 0–1")
+ p.add_argument("--confidence", type=_confidence_01, default=0.8, help="Confidence 0–1")📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| p.add_argument("--confidence", type=float, default=0.8, help="Confidence 0–1") | |
| def _confidence_01(value): | |
| v = float(value) | |
| if not 0.0 <= v <= 1.0: | |
| raise argparse.ArgumentTypeError("confidence must be between 0 and 1") | |
| return v | |
| p.add_argument("--confidence", type=_confidence_01, default=0.8, help="Confidence 0–1") |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@examples/claudecode-skills-memanto/scripts/memanto_memory.py` at line 219,
The --confidence arg currently allows any float; add validation at parse time by
replacing p.add_argument("--confidence", type=float, ...) with a validator
function (e.g., def confidence_type(v): try: f=float(v) except: raise
argparse.ArgumentTypeError(...) ; if not 0.0 <= f <= 1.0: raise
argparse.ArgumentTypeError("confidence must be between 0 and 1") ; return f) and
pass type=confidence_type to p.add_argument so parsing fails fast with a clear
error for out-of-range values; reference the p.add_argument("--confidence", ...)
call when making the change.
Comment on lines
+52
to
+63
| ``` | ||
| # Session 1 — store decisions | ||
| → python scripts/memanto_memory.py remember "Chose FastAPI" "Picked FastAPI over Flask for async support and built-in validation" | ||
|
|
||
| # Session 2 — recall before starting | ||
| → python scripts/memanto_memory.py recall "API framework decision" | ||
| → [decision] Chose FastAPI — Picked FastAPI over Flask for async… | ||
|
|
||
| # Session 3 — ask a question | ||
| → python scripts/memanto_memory.py answer "why did we pick FastAPI?" | ||
| → Chose FastAPI for async support and built-in validation | ||
| ``` |
There was a problem hiding this comment.
Add a language to the fenced code block.
The example workflow fence is missing a language tag, which trips markdown linting (MD040). Use something like ```text for this transcript-style example.
🧰 Tools
🪛 markdownlint-cli2 (0.22.1)
[warning] 52-52: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@examples/claudecode-skills-memanto/SKILL.md` around lines 52 - 63, The fenced
code block containing the example transcript (the block starting with "# Session
1 — store decisions" and the three shell lines) is missing a language tag and
triggers MD040; update the opening fence from ``` to ```text (or another
appropriate language) so the block is recognized as plain text and the markdown
linter stops flagging it.
Collaborator
|
We were blown away by the community's creativity and the sheer volume of high-quality submissions! After reviewing all the pull requests against the bounty's success matrix, we have decided to move forward with merging PR #692, which implemented a highly portable prompt-injection architecture via CLAUDE.md. We are closing this PR because it falls into one of the architectural approaches that we ultimately decided against for the ecosystem:
We deeply appreciate the time and engineering effort you put into this submission. The codebase was fantastic to review, and we hope to see you in future Moorcheh bounties! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a global memory layer for the mattpocock/skills ecosystem using Memanto.
Files
How it works
Claude reads SKILL.md ? calls python scripts/memanto_memory.py ? uses memanto's DirectClient ? stores/retrieves memories via the Moorcheh API. Cross-session persistence without needing a local server.
Social Media Showcase