Skip to content

Conversation

@jack-arturo
Copy link
Member

  • Updated the API endpoint count in CLAUDE.md from 13 to ~21.
  • Changed consolidation interval settings in CLAUDE.md to default values for better clarity.
  • Revised installation instructions in INSTALLATION.md to reflect the new Remote MCP server terminology.
  • Enhanced README.md with updated project description and visual elements.
  • Clarified API authentication methods in API.md.
  • Renamed MCP server documentation to reflect the new Remote MCP terminology.
  • Adjusted testing documentation to specify vector dimensions for Qdrant.

- Updated the API endpoint count in CLAUDE.md from 13 to ~21.
- Changed consolidation interval settings in CLAUDE.md to default values for better clarity.
- Revised installation instructions in INSTALLATION.md to reflect the new Remote MCP server terminology.
- Enhanced README.md with updated project description and visual elements.
- Clarified API authentication methods in API.md.
- Renamed MCP server documentation to reflect the new Remote MCP terminology.
- Adjusted testing documentation to specify vector dimensions for Qdrant.
@coderabbitai
Copy link

coderabbitai bot commented Jan 21, 2026

📝 Walkthrough

Summary by CodeRabbit

  • Documentation

    • Updated API auth to require tokens for most endpoints; /health remains public.
    • Replaced SSE sidecar wording with Remote MCP across README, deployment, and docs; refined testing/benchmark language.
    • Added memory metadata note (last_accessed) and clarified embedding defaults.
  • Configuration

    • Consolidation interval settings renamed and redefaulted toward much longer cycles (daily/weekly/monthly).
    • Memory forgetting disabled by default.

✏️ Tip: You can customize this high-level summary in your review settings.

Walkthrough

API and configuration defaults adjusted: consolidation intervals lengthened (decay → 1 day, creative → 1 week, cluster → 1 month, forget → disabled). API endpoint counts updated to reflect new automem/api surface (+legacy routes). MCP docs and deployment references replaced "SSE sidecar" with "Remote MCP"; API auth clarified for all endpoints except /health.

Changes

Cohort / File(s) Summary
Configuration & API surface
CLAUDE.md
Consolidation env vars renamed/retargeted and default values changed (decay 3600→86400, creative 3600→604800, cluster 21600→2592000, forget 86400→0/disabled). API endpoint description updated to reflect automem/api endpoints plus legacy app.py routes.
Deployment & MCP docs
INSTALLATION.md, docs/MCP_SSE.md, docs/RAILWAY_DEPLOYMENT.md, README.md
Replaced references to "MCP SSE sidecar"/"MCP Server Bridge" with "Remote MCP"; adjusted deployment wording. INSTALLATION.md notes embedding auto-generation defaults and memory.metadata.last_accessed. Railway checklist updated to reference Remote MCP.
API authentication docs
docs/API.md
Authentication tightened: all endpoints except /health require authentication via Bearer Authorization, X-API-Key, or ?api_key=. Admin endpoints still require X-Admin-Token.
Documentation restructuring & UI copy
README.md
README restructured: banner image, renamed sections (e.g., "Core Capabilities", "Research Foundation"), terminology harmonized to "Remote MCP" and "graph-vector", updated community/resource links, and removed dated update block.
Testing & benchmarks
docs/TESTING.md
Benchmark presentation streamlined; default vector dimensionality note updated (3072d default, 768d for small models); headings and comparison phrasing standardized; AutoMem advantages expanded.

Sequence Diagram(s)

(omitted — changes are primarily configuration and documentation updates, not new multi-component control flow)

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~12 minutes

Possibly related PRs

🚥 Pre-merge checks | ✅ 3
✅ Passed checks (3 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly summarizes the main change: documentation updates to API documentation and configuration settings across multiple files.
Description check ✅ Passed The description is directly related to the changeset, listing specific documentation updates across multiple files (CLAUDE.md, INSTALLATION.md, README.md, API.md, MCP server docs, TESTING.md).
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch docs-update-20-january

Comment @coderabbitai help to get the list of available commands and usage tips.

@coderabbitai coderabbitai bot added the enhancement New feature or request label Jan 21, 2026
Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 2

🤖 Fix all issues with AI agents
In `@CLAUDE.md`:
- Line 45: Update the endpoint count text in CLAUDE.md where it says "The API
(`app.py`) provides ~21 endpoints:" to reflect the current routes: change "~21"
to "28" to match the automem/api module breakdown (admin: 2, memory: 10, recall:
4, graph: 5, health: 1, enrichment: 2, consolidation: 2, stream: 2); also add a
short note mentioning that 12 legacy routes remain in app.py for a combined
total of 40 if both sets are active, so readers understand the distinction
between current automem/api routes and legacy routes.

In `@README.md`:
- Around line 17-18: The README currently cites an unsourced "OpenAI baseline
(39%)" comparison; either remove that phrase from README.md (search for the
literal "OpenAI baseline (39%)" and the sentence containing it) or add a
documented source in docs/TESTING.md: create a section or subsection that
records the evaluation procedure, dataset, metric and citation that produced the
39% OpenAI result, and update the README to link to that TESTING.md section;
ensure the README and docs use the exact phrasing "OpenAI baseline (39%)" so the
references stay consistent.
🧹 Nitpick comments (1)
README.md (1)

289-289: Minor wording polish for readability.

“very old” is a bit vague; consider “older” or “long-idle” for smoother phrasing.

✏️ Suggested tweak
-| **Forget**   | Disabled  | Archives low-relevance (<0.2), deletes very old (<0.05) when enabled |
+| **Forget**   | Disabled  | Archives low-relevance (<0.2), deletes older (<0.05) when enabled |

- Revised the API endpoint count in CLAUDE.md to reflect a total of 28 active endpoints, with 12 legacy routes for backward compatibility, bringing the combined total to 40.
- Updated the README.md to remove reference to OpenAI's baseline in the accuracy comparison, streamlining the project description.
Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Fix all issues with AI agents
In `@README.md`:
- Around line 462-466: Replace the bare URL
"https://www.npmjs.com/package/@verygoodplugins/mcp-automem" with a markdown
link label (e.g., [`@verygoodplugins/mcp-automem`]) so the Resources section uses
a proper markdown link instead of a raw URL; update the "NPM bridge (local):"
line accordingly to satisfy markdownlint MD034 and improve readability.

- Updated the NPM bridge link in README.md to use markdown formatting for better visibility and accessibility.
@jack-arturo jack-arturo merged commit ad9500f into main Jan 21, 2026
7 checks passed
@jack-arturo jack-arturo deleted the docs-update-20-january branch January 21, 2026 02:30
meanin2 added a commit to meanin2/automem that referenced this pull request Feb 3, 2026
Upstream commits merged:
- ad9500f docs: Update API documentation and configuration settings (verygoodplugins#51)
- 09ac4ac docs: Enhance README.md with formatted NPM bridge link
- 9e71299 docs: Update API endpoint count and project description
- 9281149 docs: Update API documentation and configuration settings
- 283aa56 Add token fee badge and update project description (verygoodplugins#50)
- 3ca46ea Add token fee badge and update project description

Our Gemini embedding provider (custom modification) is preserved.
jack-arturo added a commit that referenced this pull request Feb 6, 2026
🤖 I have created a release *beep* *boop*
---


##
[0.10.0](v0.9.3...v0.10.0)
(2026-02-06)


### Features

* Add `exclude_tags` parameter to recall API
([#58](#58))
([8aeca2e](8aeca2e))
* add memory content size governance with auto-summarization
([e24a86b](e24a86b))
* add memory content size governance with auto-summarization
([876aabf](876aabf))
* Add real-time observability with SSE streaming and TUI monitor
([54d2701](54d2701))
* Add real-time observability with SSE streaming and TUI monitor
([c5f6370](c5f6370))
* Add real-time observability with SSE streaming and TUI monitor
([944168e](944168e))
* **api:** add graph visualization API endpoints
([#26](#26))
([a0d0dd3](a0d0dd3))
* **api:** add time-based sorting to recall API
([c063845](c063845))
* **api:** add time-based sorting to recall API
([a511f0c](a511f0c))
* create coderabbit.yml
([e05811f](e05811f))
* **embedding:** add Ollama embedding provider and expand docs
([#56](#56))
([b506a90](b506a90))
* **mcp-sse:** agent-friendly recall output + tests
([71201d3](71201d3))
* **mcp-sse:** improve recall tool output and options
([97c4f72](97c4f72))


### Bug Fixes

* Add TTL cleanup to InMemoryEventStore
([0631af6](0631af6))
* Address CodeRabbit security and lint issues
([a701c57](a701c57))
* **backup:** Fix GitHub Actions backup failing with connection error
([19ed1e8](19ed1e8))
* **backup:** Fix GitHub Actions backup failing with connection error
([10b37d0](10b37d0))
* **consolidation:** prevent accidental forgetting
([4330c20](4330c20))
* **consolidation:** prevent accidental forgetting
([39dee3e](39dee3e))
* Correct token parameter for gpt-5 models (max_output_tokens)
([0786705](0786705))
* **enrichment:** sync tags/tag_prefixes to Qdrant
([3ccf874](3ccf874))
* **enrichment:** sync tags/tag_prefixes to Qdrant
([7ba9d76](7ba9d76))
* Handle streamable HTTP client disconnects
([f15a7ee](f15a7ee))
* **mcp-sse:** update test for SDK 1.20+ Accept header behavior
([597909e](597909e))
* **mcp:** close transport/server on sweep and update Accept header test
([ce7f6fa](ce7f6fa))
* **mcp:** replace broken res.on('close') with TTL sweep for Streamable
HTTP sessions
([3d53263](3d53263))
* **mcp:** replace broken res.on('close') with TTL sweep for Streamable
HTTP sessions
([#59](#59))
([d4d3259](d4d3259))
* **mcp:** use Promise.resolve().catch() for async close() in session
sweep
([a8cc589](a8cc589))
* Production bugs - datetime tz, OpenAI tokens, Qdrant race
([14491c4](14491c4))
* Production bugs - datetime tz, OpenAI tokens, Qdrant race
([0771360](0771360))
* Refactor tests to use double quotes for consistency
([21da453](21da453))
* Refine summarization token limit and improve tests
([6cab145](6cab145))
* Update test for POST /mcp Accept header error
([67a5a10](67a5a10))
* YAML indentation in backup workflow and update docs
([a606b3e](a606b3e))


### Documentation

* add mermaid diagrams for architecture visualization
([0d70a2a](0d70a2a))
* Add Qdrant setup guide and update docs for AUTOMEM_API_URL
([5c440aa](5c440aa))
* Add Qdrant setup guide and update docs for AUTOMEM_API_URL
([123ff28](123ff28))
* Enhance README.md with formatted NPM bridge link
([09ac4ac](09ac4ac))
* merge mermaid diagrams from docs/add-mermaid-diagrams
([4e9ae4f](4e9ae4f))
* Update API documentation and configuration settings
([9281149](9281149))
* Update API documentation and configuration settings
([#51](#51))
([ad9500f](ad9500f))
* Update API endpoint count and project description
([9e71299](9e71299))
* update diagrams for Streamable HTTP transport
([1a2ce22](1a2ce22))
* Update docs to clarify MCP bridge and improve formatting
([af69a2f](af69a2f))
* Update MCP documentation and server implementation for Streamable HTTP
support
([8fdef09](8fdef09))
* Update MCP documentation and server implementation for Streamable HTTP
support
([335a78d](335a78d))
* update MCP_SSE.md to reflect MCP bridge terminology
([940a776](940a776))
* Update Railway deployment docs and improve README
([5480eb5](5480eb5))
* Update Railway deployment docs and improve README
([82c33b0](82c33b0))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Jack Arturo <info@verygoodplugins.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Documentation: Clarify Railway deployment and API token configuration

1 participant