Skip to content

docs: rewrite README for v0.3.0 — what, why, and agent support#5

Merged
rohitg00 merged 4 commits intomainfrom
rohit/readme-v0.3.0-rewrite
Feb 27, 2026
Merged

docs: rewrite README for v0.3.0 — what, why, and agent support#5
rohitg00 merged 4 commits intomainfrom
rohit/readme-v0.3.0-rewrite

Conversation

@rohitg00
Copy link
Copy Markdown
Owner

@rohitg00 rohitg00 commented Feb 27, 2026

Summary

  • Rewrites README to clearly explain what agentmemory provides and why someone would choose it over CLAUDE.md or claude-mem
  • Adds Supported Agents section covering native hooks (Claude Code), MCP (Cursor, Windsurf, Cline, etc.), and REST API (any agent/language)
  • Adds decision matrix for choosing the right integration method
  • Documents all v0.3.0 capabilities: hybrid search, 6 embedding providers, memory evolution, project profiles, auto-forget, timeline, export/import
  • Updates all stats to reflect v0.3.0 (21 functions, 10 MCP tools, 28 endpoints, 144 tests, 126KB bundle)

Test plan

  • Verify README renders correctly on GitHub
  • Check all internal anchor links work
  • Confirm stats match actual codebase

Summary by CodeRabbit

  • Documentation
    • Updated README with refreshed introduction highlighting persistent memory capabilities.
    • Reorganized navigation to feature Search, Memory Evolution, and integration methods.
    • Expanded feature documentation including Semantic Search, Auto-forgetting, Privacy, Self-healing, and Observability.
    • Revised Quick Start guides and integration instructions with updated commands.
    • Enhanced API and integration sections with new endpoints and methods.

- Add "Why agentmemory" section explaining what it provides and comparison table
- Add "Supported Agents" section with native hooks, MCP, and REST API paths
- Add integration decision matrix for choosing the right approach
- Document hybrid search, embedding providers, and progressive disclosure
- Document memory evolution, versioning, relationships, and auto-forget
- Document project profiles, timeline, export/import
- Update all stats (21 functions, 10 MCP tools, 28 endpoints, 144 tests)
- Update data model with new KV scopes (relations, profiles, embeddings, bm25)
- Update config section with embedding, fallback, and search weight env vars
@coderabbitai
Copy link
Copy Markdown

coderabbitai Bot commented Feb 27, 2026

Warning

Rate limit exceeded

@rohitg00 has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 25 minutes and 22 seconds before requesting another review.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

📥 Commits

Reviewing files that changed from the base of the PR and between 7b036d0 and 272dddf.

⛔ Files ignored due to path filters (1)
  • assets/banner.png is excluded by !**/*.png
📒 Files selected for processing (1)
  • README.md
📝 Walkthrough

Walkthrough

README.md underwent comprehensive restructuring: header presentation changed to centered banner; navigation anchors reorganized; introductory narrative reframed around persistent memory architecture; feature sections expanded to include semantic search, memory evolution, and project profiles; integration guidance updated for multiple methods; quick start examples and command references refreshed; and data model architecture expanded with embeddings and memory relationships documentation.

Changes

Cohort / File(s) Summary
Documentation Restructuring
README.md
Replaced textual header with centered banner image; reorganized navigation anchors (removed Self-Evaluation, MCP Server, Skills; added Search, Memory Evolution); rewrote introductory narrative with new "Why agentmemory" section emphasizing persistent memory via architecture re-collection; expanded feature sections with Semantic search, Memory Evolution, Project Profiles, Auto-forgetting, Privacy, Self-healing, Observability; updated integration guidance for Hooks + MCP and REST API methods; refreshed Quick Start examples with new commands and agent terminology; introduced memory-centric command surface with endpoints (smart-search, timeline, relate/evolve, auto-forget); expanded MCP tool list; updated data model references to include embeddings, BM25 indexes, and memory relationships; adjusted development metrics and build commands.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Poem

🐰 A banner now waves at the top,
With search and memory that won't stop,
No more forgetting between the sessions,
Just persistent wisdom and blessed progressions!
The README's reborn, more vibrant and bright—
Agent memories now holding tight! 🌟

🚥 Pre-merge checks | ✅ 3
✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The pull request title clearly and specifically describes the main change: a README rewrite for v0.3.0 that explains what the project is, why to use it, and adds agent support documentation.
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 rohit/readme-v0.3.0-rewrite

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

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

Remove cream strip at bottom, cap width to 720px in README
Copy link
Copy Markdown

@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

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)
README.md (1)

28-40: ⚠️ Potential issue | 🟡 Minor

Add language identifiers to fenced code blocks to satisfy lint and improve rendering consistency.

The fences starting at Line 28, Line 201, Line 276, and Line 349 are missing language tags (MD040). Use text for flow/pipeline blocks.

Suggested diff
-```
+```text
 Session 1: "Add auth to the API"
   Agent writes code, runs tests, fixes bugs
   agentmemory silently captures every tool use
   Session ends -> observations compressed into structured memory
@@
-```
+```text
 SessionStart hook fires
   -> mem::context     Load recent sessions for this project
@@
-```
+```text
 v1: "Use Express for API routes"
 v2: "Use Fastify instead of Express for API routes" (supersedes v1)
 v3: "Use Hono instead of Fastify for Edge API routes" (supersedes v2)
@@
-```
+```text
 Primary provider fails
   -> Circuit breaker opens (3 failures in 60s)
   -> Falls back to next provider in FALLBACK_PROVIDERS chain
   -> 30s cooldown -> half-open -> test call -> recovery

Also applies to: 201-208, 276-280, 349-354

🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@README.md` around lines 28 - 40, Update the four fenced code blocks by adding
the language tag `text` after the opening backticks — specifically change the
blocks that begin with "Session 1: \"Add auth to the API\"", "SessionStart hook
fires", "v1: \"Use Express for API routes\"", and "Primary provider fails" so
each opens with ```text instead of ```, which will satisfy MD040 and ensure
consistent rendering.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@README.md`:
- Line 74: The sentence "agentmemory works with any agent that supports hooks or
MCP." should be reworded to include REST API support so the contract is
consistent; change that line to e.g. "agentmemory works with any agent that
supports hooks, MCP, or via a REST API." Also update the later paragraph (the
section currently describing REST support at lines ~97-100) to mirror this
wording and explicitly state that agents without hooks/MCP can integrate using
the REST API, ensuring both places use the same phrasing and intent.

---

Outside diff comments:
In `@README.md`:
- Around line 28-40: Update the four fenced code blocks by adding the language
tag `text` after the opening backticks — specifically change the blocks that
begin with "Session 1: \"Add auth to the API\"", "SessionStart hook fires", "v1:
\"Use Express for API routes\"", and "Primary provider fails" so each opens with
```text instead of ```, which will satisfy MD040 and ensure consistent
rendering.

ℹ️ Review info

Configuration used: defaults

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between dbe421c and 7b036d0.

⛔ Files ignored due to path filters (1)
  • assets/banner.png is excluded by !**/*.png
📒 Files selected for processing (1)
  • README.md

Comment thread README.md Outdated
Consistent wording in both the intro line and REST section
@rohitg00 rohitg00 merged commit 367d419 into main Feb 27, 2026
1 check was pending
@rohitg00 rohitg00 deleted the rohit/readme-v0.3.0-rewrite branch February 27, 2026 05:22
rohitg00 added a commit that referenced this pull request Feb 27, 2026
* docs: rewrite README for v0.3.0

- Add "Why agentmemory" section explaining what it provides and comparison table
- Add "Supported Agents" section with native hooks, MCP, and REST API paths
- Add integration decision matrix for choosing the right approach
- Document hybrid search, embedding providers, and progressive disclosure
- Document memory evolution, versioning, relationships, and auto-forget
- Document project profiles, timeline, export/import
- Update all stats (21 functions, 10 MCP tools, 28 endpoints, 144 tests)
- Update data model with new KV scopes (relations, profiles, embeddings, bm25)
- Update config section with embedding, fallback, and search weight env vars

* docs: add banner image to README

* docs: fix banner crop and size

Remove cream strip at bottom, cap width to 720px in README

* docs: include REST API in supported agents intro

Consistent wording in both the intro line and REST section
@coderabbitai coderabbitai Bot mentioned this pull request Mar 4, 2026
2 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant