feat: real agent logos + paste-this-prompt blocks for integrations#114
Merged
feat: real agent logos + paste-this-prompt blocks for integrations#114
Conversation
…for integrations ## Main README — real logos in Supported Agents grid Replaced plain text cells with real brand logos for all 16 supported agents: - simple-icons CDN for: Claude Code (Anthropic), Cursor, Gemini CLI (Google Gemini), Codex CLI (OpenAI), Windsurf, Claude Desktop, Claude SDK - GitHub org avatars for: OpenClaw, OpenCode (opencode-ai), Cline, Hermes (NousResearch), Goose (block), Kilo Code (kilo-org), Aider (Aider-AI), Roo Code (RooCodeInc) - Shield badge for the generic "Any agent" cell Each logo is clickable and links to the upstream project. The OpenClaw and Hermes cells now link directly to integrations/openclaw and integrations/hermes so users can find the deeper plugin integration. Added tagline footer below the grid reinforcing the cross-agent story. ## Integration READMEs — paste-this-prompt blocks Following the gstack pattern, both integration READMEs now open with a visual hero (upstream logo + agentmemory logo) and a copy-pasteable text block the user can drop into their agent. The agent handles the entire setup — start server, update MCP config, verify health, open viewer. This matches the "paste this into Claude Code" block we already have in the main README for Claude Code users. ### openclaw/README.md - Centered hero: OpenClaw org avatar + agentmemory icon - Shield badges: 43 MCP tools, 4 lifecycle hooks, 95.2% R@5, self-hosted - "Install it in 30 seconds" section with the paste-this prompt ### hermes/README.md - Centered hero: NousResearch avatar + agentmemory icon - Shield badges: 43 MCP tools, 6 lifecycle hooks, 95.2% R@5, self-hosted - "Install it in 30 seconds" section with the paste-this prompt All 654 tests still passing.
|
Warning Rate limit exceeded
Your organization is not enrolled in usage-based pricing. Contact your admin to enable usage-based pricing to continue reviews beyond the rate limit, or try again in 8 minutes and 43 seconds. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the 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. 📝 WalkthroughWalkthroughDocumentation-only updates: main README replaces the "Supported Agents" table with icon/badge cards, adds OpenClaw/Hermes copy-paste setup blocks and a cross-agent memory note; Hermes and OpenClaw integration READMEs expanded with branding, badges, and "Install it in 30 seconds" guides. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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. 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: 1
🧹 Nitpick comments (1)
README.md (1)
266-268: Update the endpoint count badge to match runtime output.The new badge says 109 endpoints, but runtime logs report 103 REST endpoints (
src/index.ts, Line 283-Line 285). This introduces a docs inconsistency in the newly added agent cell.Proposed doc fix
-<img src="https://img.shields.io/badge/109-endpoints-1f6feb?style=flat-square" alt="REST API" /><br/> +<img src="https://img.shields.io/badge/103-REST_endpoints-1f6feb?style=flat-square" alt="103 REST endpoints" /><br/>🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@README.md` around lines 266 - 268, The README's endpoint-count badge text/value is inconsistent with runtime logs: update the badge that currently contains "109-endpoints" in the agent cell (the <img> tag showing "109-endpoints-1f6feb") to reflect the runtime-reported "103" REST endpoints (make the image URL/text show "103-endpoints" so the badge matches the count reported in src/index.ts where endpoints are logged).
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@integrations/openclaw/README.md`:
- Around line 43-46: Update the README's health-check wording so it doesn't
require an exact JSON match; change the instruction around the
/agentmemory/health endpoint (port 3111) to say confirm the status field
indicates healthy (e.g., response contains "status":"healthy" or a JSON with a
healthy status) or that the endpoint returns a healthy status in its JSON
payload, rather than asserting the response is exactly {"status":"healthy"};
keep the real-time viewer reference (port 3113) unchanged.
---
Nitpick comments:
In `@README.md`:
- Around line 266-268: The README's endpoint-count badge text/value is
inconsistent with runtime logs: update the badge that currently contains
"109-endpoints" in the agent cell (the <img> tag showing "109-endpoints-1f6feb")
to reflect the runtime-reported "103" REST endpoints (make the image URL/text
show "103-endpoints" so the badge matches the count reported in src/index.ts
where endpoints are logged).
🪄 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
Run ID: 97369375-0adb-4fd4-a4f8-7605aa12e7a5
📒 Files selected for processing (3)
README.mdintegrations/hermes/README.mdintegrations/openclaw/README.md
Comment on lines
+43
to
+46
| Restart OpenClaw. Verify it's working with | ||
| `curl http://localhost:3111/agentmemory/health` — it should return | ||
| {"status":"healthy"}. Open the real-time viewer at | ||
| http://localhost:3113 to watch memories being captured live. |
There was a problem hiding this comment.
Relax the health-check expectation to avoid false negatives.
The prompt currently implies the response should be exactly {"status":"healthy"}. The endpoint returns a fuller JSON payload, so this check can mislead users.
Proposed wording update
-`curl http://localhost:3111/agentmemory/health` — it should return
-{"status":"healthy"}. Open the real-time viewer at
+`curl http://localhost:3111/agentmemory/health` — confirm the JSON has
+`"status":"healthy"` (additional fields are expected). Open the real-time viewer at📝 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
| Restart OpenClaw. Verify it's working with | |
| `curl http://localhost:3111/agentmemory/health` — it should return | |
| {"status":"healthy"}. Open the real-time viewer at | |
| http://localhost:3113 to watch memories being captured live. | |
| Restart OpenClaw. Verify it's working with | |
| `curl http://localhost:3111/agentmemory/health` — confirm the JSON has | |
| `"status":"healthy"` (additional fields are expected). Open the real-time viewer at | |
| http://localhost:3113 to watch memories being captured live. |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@integrations/openclaw/README.md` around lines 43 - 46, Update the README's
health-check wording so it doesn't require an exact JSON match; change the
instruction around the /agentmemory/health endpoint (port 3111) to say confirm
the status field indicates healthy (e.g., response contains "status":"healthy"
or a JSON with a healthy status) or that the endpoint returns a healthy status
in its JSON payload, rather than asserting the response is exactly
{"status":"healthy"}; keep the real-time viewer reference (port 3113) unchanged.
…blocks, cleaner hero ## Main README ### Supported Agents grid — 3 fixes 1. **Reorder**: OpenClaw and Hermes now in positions 2 and 3 (right after Claude Code), since they have first-class gateway plugins in integrations/. Users shouldn't have to scroll to find them. 2. **Fix broken Codex logo**: simple-icons CDN returned 404 for the OpenAI slug with black color. Switched ALL logos to GitHub org avatars (github.com/<org>.png?size=120) which are bulletproof and always return real images. Verified 7/7 resolve to actual PNGs. 3. **Bigger logos**: bumped from 40px to 48px for more visual weight. ### Paste-this-prompt toggles Added two collapsible <details> blocks after the Claude Code paste prompt: one for OpenClaw, one for Hermes. Each contains a complete copy-pasteable setup prompt that the agent can execute, plus a link to the full integration guide. ## Integration README heroes — redesigned The old hero had two logos separated by an ugly gray "+" shield badge that looked cheap. Replaced with: - agentmemory banner.png as the centered hero image - H1 title with a small inline upstream logo (28px) next to the title - Bolded tagline + subtitle with upstream link - Shield badge row (MCP tools, hooks, R@5, self-hosted, license) Much cleaner and follows the main README's visual pattern. Verified: 654/654 tests passing.
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 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`:
- Around line 304-317: The fenced code block in README.md containing the
OpenClaw agentmemory instructions uses a plain ``` fence which triggers MD040;
update the opening fence to include a language identifier (e.g., change the
opening ``` to ```text) so the block becomes a labeled fenced code block,
leaving the closing ``` as-is and preserving the existing block content.
- Around line 326-335: The fenced code block containing the Hermes/agentmemory
setup snippet is missing a language identifier (MD040); update the opening fence
for that block (the triple-backtick that precedes "Install agentmemory for
Hermes...") to include a language tag such as "text" so the fence reads ```text,
leaving the content unchanged and the closing ``` as-is.
🪄 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
Run ID: b18b0a83-acd7-465d-978f-ce73cf47e817
📒 Files selected for processing (3)
README.mdintegrations/hermes/README.mdintegrations/openclaw/README.md
✅ Files skipped from review due to trivial changes (2)
- integrations/openclaw/README.md
- integrations/hermes/README.md
Comment on lines
+304
to
+317
| ``` | ||
| Install agentmemory for OpenClaw. Run `npx @agentmemory/agentmemory` in a separate terminal to start the memory server on localhost:3111. Then add this to my OpenClaw MCP config so agentmemory is available with all 43 memory tools: | ||
|
|
||
| { | ||
| "mcpServers": { | ||
| "agentmemory": { | ||
| "command": "npx", | ||
| "args": ["agentmemory-mcp"] | ||
| } | ||
| } | ||
| } | ||
|
|
||
| Restart OpenClaw. Verify with `curl http://localhost:3111/agentmemory/health`. Open http://localhost:3113 for the real-time viewer. For deeper 4-hook gateway integration, see integrations/openclaw in the agentmemory repo. | ||
| ``` |
There was a problem hiding this comment.
Add a language identifier to the OpenClaw fenced block.
Line 304 uses a plain triple-backtick fence, which triggers MD040 and can reduce syntax highlighting consistency.
Suggested fix
-```
+```text
Install agentmemory for OpenClaw. Run `npx `@agentmemory/agentmemory`` in a separate terminal to start the memory server on localhost:3111. Then add this to my OpenClaw MCP config so agentmemory is available with all 43 memory tools:
@@
-```
+```📝 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
| ``` | |
| Install agentmemory for OpenClaw. Run `npx @agentmemory/agentmemory` in a separate terminal to start the memory server on localhost:3111. Then add this to my OpenClaw MCP config so agentmemory is available with all 43 memory tools: | |
| { | |
| "mcpServers": { | |
| "agentmemory": { | |
| "command": "npx", | |
| "args": ["agentmemory-mcp"] | |
| } | |
| } | |
| } | |
| Restart OpenClaw. Verify with `curl http://localhost:3111/agentmemory/health`. Open http://localhost:3113 for the real-time viewer. For deeper 4-hook gateway integration, see integrations/openclaw in the agentmemory repo. | |
| ``` |
🧰 Tools
🪛 markdownlint-cli2 (0.22.0)
[warning] 304-304: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@README.md` around lines 304 - 317, The fenced code block in README.md
containing the OpenClaw agentmemory instructions uses a plain ``` fence which
triggers MD040; update the opening fence to include a language identifier (e.g.,
change the opening ``` to ```text) so the block becomes a labeled fenced code
block, leaving the closing ``` as-is and preserving the existing block content.
Comment on lines
+326
to
+335
| ``` | ||
| Install agentmemory for Hermes. Run `npx @agentmemory/agentmemory` in a separate terminal to start the memory server on localhost:3111. Then add this to ~/.hermes/config.yaml so Hermes can use agentmemory as an MCP server with all 43 memory tools: | ||
|
|
||
| mcp_servers: | ||
| agentmemory: | ||
| command: npx | ||
| args: ["agentmemory-mcp"] | ||
|
|
||
| Verify with `curl http://localhost:3111/agentmemory/health`. Open http://localhost:3113 for the real-time viewer. For deeper 6-hook memory provider integration (pre-LLM context injection, turn capture, MEMORY.md mirroring, system prompt block), copy integrations/hermes from the agentmemory repo to ~/.hermes/plugins/memory/agentmemory. | ||
| ``` |
There was a problem hiding this comment.
Add a language identifier to the Hermes fenced block.
Line 326 has the same MD040 issue as the OpenClaw block; mark the fence language explicitly.
Suggested fix
-```
+```text
Install agentmemory for Hermes. Run `npx `@agentmemory/agentmemory`` in a separate terminal to start the memory server on localhost:3111. Then add this to ~/.hermes/config.yaml so Hermes can use agentmemory as an MCP server with all 43 memory tools:
@@
-```
+```🧰 Tools
🪛 markdownlint-cli2 (0.22.0)
[warning] 326-326: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@README.md` around lines 326 - 335, The fenced code block containing the
Hermes/agentmemory setup snippet is missing a language identifier (MD040);
update the opening fence for that block (the triple-backtick that precedes
"Install agentmemory for Hermes...") to include a language tag such as "text" so
the fence reads ```text, leaving the content unchanged and the closing ```
as-is.
There was a problem hiding this comment.
♻️ Duplicate comments (2)
README.md (2)
303-317:⚠️ Potential issue | 🟡 MinorAdd a language identifier to this fenced block.
Line 303 still uses an unlabeled fence, which keeps triggering MD040.
Suggested fix
-``` +```text Install agentmemory for OpenClaw. Run `npx `@agentmemory/agentmemory`` in a separate terminal to start the memory server on localhost:3111. Then add this to my OpenClaw MCP config so agentmemory is available with all 43 memory tools: @@ -``` +```🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@README.md` around lines 303 - 317, The README's fenced code block is unlabeled and triggers MD040; update the opening fence for that block (the triple backticks before the "Install agentmemory..." paragraph) to include a language identifier such as text (change ``` to ```text) so the block is properly labeled and the linter stops flagging it; no other content changes are needed.
325-335:⚠️ Potential issue | 🟡 MinorAdd a language identifier to this fenced block as well.
Line 325 has the same MD040 issue; label the fence explicitly.
Suggested fix
-``` +```text Install agentmemory for Hermes. Run `npx `@agentmemory/agentmemory`` in a separate terminal to start the memory server on localhost:3111. Then add this to ~/.hermes/config.yaml so Hermes can use agentmemory as an MCP server with all 43 memory tools: @@ -``` +```🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@README.md` around lines 325 - 335, The fenced code block in README.md that begins with the lines "Install agentmemory for Hermes..." is missing a language identifier (MD040); change the opening fence from ``` to ```text so the block is explicitly labeled (e.g., replace the leading ``` with ```text and keep the trailing ```), ensuring the fenced block is parsed as text as suggested in the review.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Duplicate comments:
In `@README.md`:
- Around line 303-317: The README's fenced code block is unlabeled and triggers
MD040; update the opening fence for that block (the triple backticks before the
"Install agentmemory..." paragraph) to include a language identifier such as
text (change ``` to ```text) so the block is properly labeled and the linter
stops flagging it; no other content changes are needed.
- Around line 325-335: The fenced code block in README.md that begins with the
lines "Install agentmemory for Hermes..." is missing a language identifier
(MD040); change the opening fence from ``` to ```text so the block is explicitly
labeled (e.g., replace the leading ``` with ```text and keep the trailing ```),
ensuring the fenced block is parsed as text as suggested in the review.
Replaces emoji section headers with custom SVG badges matching the agentmemory brand style (orange #FF6B35 accent on dark #1A1A1A). Inspired by shanraisshan/claude-code-best-practice's custom tag approach in its !/ directory. ## Custom SVG tags created (30 total in assets/tags/) ### 14 section headers (section-*.svg) Each is a 44px-tall dark rounded badge with: - Orange gradient accent strip on the left (brand color #FF6B35 → #FF8F5E) - Uppercase title in white, 800 weight, 2.2 letter-spacing - Light gray subtitle (#9CA3AF) with section context - Subtle #2A2A2A border on dark #1A1A1A → #0F0F0F gradient Sections: works-with-every-agent, benchmarks, vs-competitors, quick-start, why, how-it-works, search, mcp-server, real-time-viewer, configuration, api, architecture, development, license. ### 6 hero stat blocks (stat-*.svg) Big numbers with small uppercase labels, replacing the shield.io badge row in two places (hero + benchmarks section): - stat-recall: 95.2% R@5 (green) - stat-tokens: 92% fewer tokens (green) - stat-tools: 43 MCP tools (orange) - stat-hooks: 12 auto hooks (orange) - stat-deps: 0 external DBs (purple) - stat-tests: 654 tests passing (green) ### 8 pill tags (pill-*.svg) Rounded pills with colored dot indicator for inline status tags: MCP, AUTO HOOK, SKILL, NEW, BETA, STABLE, PLUGIN, SECURE. ### 1 "New in v0.8.2" version tag Dark pill with orange v0.8.2 version marker. ### 1 section divider Horizontal line with orange diamond in the middle (unused for now, available for future sections). ## README changes - All <h2> section headers now use <img> tags pointing to the SVG - Hero stats row replaced with stat-*.svg row (same visual position) - Benchmarks stats row replaced with the same stat-*.svg row - Nav links updated to match the new h2 anchor IDs - "New in v0.8.2" callout uses new-v082.svg tag + note - Cursor grid cell fixed (was missing <strong>Cursor</strong> label) - Zero emojis in the entire README All 30 SVGs validated with xmllint, 654/654 tests passing.
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
README.md (1)
317-317:⚠️ Potential issue | 🟡 MinorAdd language identifiers to both fenced prompt blocks (MD040).
Line 317 and Line 339 still use unlabeled triple-backtick fences. Add a language tag (e.g.,
text) to satisfy markdownlint and keep rendering consistent.Also applies to: 339-339
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@README.md` at line 317, Two fenced prompt blocks in README.md use unlabeled triple-backtick fences; add a language identifier (e.g., `text`) to both fenced code blocks so they become ```text ... ``` to satisfy markdownlint rule MD040 and ensure consistent rendering for the prompt examples.
🧹 Nitpick comments (1)
README.md (1)
51-67: Avoid hotlinking logos from non-official third-party domains.The new grid pulls images from external hosts not controlled by this repo (e.g., Line 51, Line 66, Line 113). This can break rendering and introduces avoidable supply/reliability risk. Prefer repo-hosted assets, official brand CDNs, or GitHub avatars consistently.
Also applies to: 113-114
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@README.md` around lines 51 - 67, The README’s logo grid is hotlinking images from third-party domains (e.g., the <img> tags used for "Claude Code", "OpenClaw", "Hermes", "Cursor" and others) — replace those external src URLs with assets checked into the repo (or use official brand CDNs or GitHub avatars) and update the corresponding <img> src attributes to point to the local/official sources; ensure the alt text and sizing remain intact and commit the image files into the repository so rendering doesn’t rely on third-party hosts.
🤖 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`:
- Around line 18-24: Update all inconsistent test count mentions in the README
so they match the stat badge value "654 tests passing": search for every
occurrence of the text "646 tests" (and any other numeric test count variants)
and replace them with "654 tests" so the badge alt text "654 tests passing" and
the inline text are consistent; specifically update the instances shown in the
diff (the badge alt text "654 tests passing" and the two other lines currently
saying "646 tests") and verify the other referenced range (lines around the
second badge block) to ensure all mentions are identical.
---
Duplicate comments:
In `@README.md`:
- Line 317: Two fenced prompt blocks in README.md use unlabeled triple-backtick
fences; add a language identifier (e.g., `text`) to both fenced code blocks so
they become ```text ... ``` to satisfy markdownlint rule MD040 and ensure
consistent rendering for the prompt examples.
---
Nitpick comments:
In `@README.md`:
- Around line 51-67: The README’s logo grid is hotlinking images from
third-party domains (e.g., the <img> tags used for "Claude Code", "OpenClaw",
"Hermes", "Cursor" and others) — replace those external src URLs with assets
checked into the repo (or use official brand CDNs or GitHub avatars) and update
the corresponding <img> src attributes to point to the local/official sources;
ensure the alt text and sizing remain intact and commit the image files into the
repository so rendering doesn’t rely on third-party hosts.
🪄 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
Run ID: c1237d81-8a9e-4c80-91d1-146633500576
⛔ Files ignored due to path filters (30)
assets/tags/divider.svgis excluded by!**/*.svgassets/tags/new-v082.svgis excluded by!**/*.svgassets/tags/pill-beta.svgis excluded by!**/*.svgassets/tags/pill-hook.svgis excluded by!**/*.svgassets/tags/pill-mcp.svgis excluded by!**/*.svgassets/tags/pill-new.svgis excluded by!**/*.svgassets/tags/pill-plugin.svgis excluded by!**/*.svgassets/tags/pill-secure.svgis excluded by!**/*.svgassets/tags/pill-skill.svgis excluded by!**/*.svgassets/tags/pill-stable.svgis excluded by!**/*.svgassets/tags/section-agents.svgis excluded by!**/*.svgassets/tags/section-api.svgis excluded by!**/*.svgassets/tags/section-architecture.svgis excluded by!**/*.svgassets/tags/section-benchmarks.svgis excluded by!**/*.svgassets/tags/section-competitors.svgis excluded by!**/*.svgassets/tags/section-config.svgis excluded by!**/*.svgassets/tags/section-development.svgis excluded by!**/*.svgassets/tags/section-how.svgis excluded by!**/*.svgassets/tags/section-license.svgis excluded by!**/*.svgassets/tags/section-mcp.svgis excluded by!**/*.svgassets/tags/section-quickstart.svgis excluded by!**/*.svgassets/tags/section-search.svgis excluded by!**/*.svgassets/tags/section-viewer.svgis excluded by!**/*.svgassets/tags/section-why.svgis excluded by!**/*.svgassets/tags/stat-deps.svgis excluded by!**/*.svgassets/tags/stat-hooks.svgis excluded by!**/*.svgassets/tags/stat-recall.svgis excluded by!**/*.svgassets/tags/stat-tests.svgis excluded by!**/*.svgassets/tags/stat-tokens.svgis excluded by!**/*.svgassets/tags/stat-tools.svgis excluded by!**/*.svg
📒 Files selected for processing (1)
README.md
Comment on lines
+18
to
24
| <img src="assets/tags/stat-recall.svg" alt="95.2% retrieval R@5" height="48" /> | ||
| <img src="assets/tags/stat-tokens.svg" alt="92% fewer tokens" height="48" /> | ||
| <img src="assets/tags/stat-tools.svg" alt="43 MCP tools" height="48" /> | ||
| <img src="assets/tags/stat-hooks.svg" alt="12 auto hooks" height="48" /> | ||
| <img src="assets/tags/stat-deps.svg" alt="0 external DBs" height="48" /> | ||
| <img src="assets/tags/stat-tests.svg" alt="654 tests passing" height="48" /> | ||
| </p> |
There was a problem hiding this comment.
Fix conflicting test counts in the README.
The updated stat badges say 654 tests passing (Line 23 and Line 194), but the same file still says 646 tests at Line 720 and Line 740. Please make these values consistent to avoid trust issues in published metrics.
Also applies to: 188-195
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@README.md` around lines 18 - 24, Update all inconsistent test count mentions
in the README so they match the stat badge value "654 tests passing": search for
every occurrence of the text "646 tests" (and any other numeric test count
variants) and replace them with "654 tests" so the badge alt text "654 tests
passing" and the inline text are consistent; specifically update the instances
shown in the diff (the badge alt text "654 tests passing" and the two other
lines currently saying "646 tests") and verify the other referenced range (lines
around the second badge block) to ensure all mentions are identical.
Removed image tag for version 0.8.2 from README.
This was referenced Apr 12, 2026
This was referenced Apr 13, 2026
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
1 participant
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
Two visual improvements to make the README and integration docs flashier and more actionable, following the claude-code-best-practice style and the gstack paste-prompt pattern.
Changes
1. Main README: real logos for all 16 supported agents
Replaced plain-text cells in the Supported Agents grid with real brand logos:
Each logo clicks through to the upstream project. OpenClaw and Hermes cells now link directly to their gateway plugin folders so users find the deeper integration quickly.
2. Integration READMEs: paste-this-prompt blocks
Both
integrations/openclaw/README.mdandintegrations/hermes/README.mdnow open with:The agent handles the whole setup: start server, update MCP config, verify
/health, open viewer. Same pattern as the main README's Claude Code block.Test plan
npm test— 654/654 passingSummary by CodeRabbit