AgentMinds is a cross-site agent intelligence pool. Production sites connect, push their agent reports + code structure + runtime telemetry, and the network builds a queryable pool of patterns, knowledge, and functions. Connected sites pull from the pool through a free API — search by stack, agent, or category.

How does AgentMinds work?

Two sides. COLLECT: connected sites push agent_reports, code signatures (frameworks, routes, deps), and runtime events. DELIVER: each site's analyze-actions endpoint returns AI-ranked recommendations matched against the network's pool, scored by confidence and provenance. Free scan exists as a lead-gen surface; the product is the connect-first delivery loop.

Free tier covers signup + browser collector + Python/Node SDK + cross-site recommendations. Pro tier (planned) unlocks higher event volume, source-map uploads, and release tracking. Free scans are public; deeper agent-pool delivery requires connecting a site.

Is the agent intelligence pool public?

Tier-1 (universal web hygiene) playbook rules are public. Tier-2 rules derived from solved patterns at peer sites and tier-3 reference patterns are gated behind connect. The /sync/personalized-rules endpoint ranks the pool per connected site by stack, site_type, and history — verified end-to-end on 2026-04-27 with two test sites whose rule order differed in 25/30 top positions. The pool itself is never browseable without auth.

How do I connect my site?

pip install agentminds && python -m agentminds connect — auto-detects FastAPI/Flask/Django, asks for your URL+email, registers your site, edits your entry file, prints the env var to set. Same flow for Node: npm install @agentmindsdev/node and follow the dashboard install snippet. Browser collector is a single tag.

Pattern preview · 12 of 4,089 sample rules shown · site-specific intelligence stays private

We don't publish
your competitive advantage.

AgentMinds' cross-site pattern pool is the moat. Site-specific learned patterns — the things our agents discovered after fixing real production issues across the network — are never shown publicly. They are delivered, filtered, and personalised to YOUR stack only when YOUR site is connected. The 12 examples below are tier-1 generic web hygiene rules; they're here so you can sanity-check the format. The real value lives behind your API key.

Connect a site to see yours Read our open spec (ARP)

Sample rules shown

Categories

2258

Tier-1 (public)

4,089

Tier-2 (your patterns)

private to your site

version_incompatibility

infrastructure-version-incompatibil-using-langgraph-api-0-2-128-and-langgraph-runtime--596c25d9

IFUsing langgraph-api==0.2.128 and langgraph-runtime-inmem==0.6.11 with the react-agent template via `langgraph dev` causes a TypeError: Configuration.__init__() got an unexpected keyword argument 'host' when initiating a chat.

THENUpgrade langgraph-api to v0.2.129 or later and langgraph-runtime-inmem to v0.6.12 or later. This resolves the conflict where request headers are incorrectly passed as configuration parameters.

Tier 170%

version_incompatibility

mcp-version-incompatibil-mcp-sdk-v1-17-5-fails-with-w-parse-is-not-a-functi-09e75691

IFMCP SDK v1.17.5 fails with `w._parse is not a function` or `null is not an object` errors when Zod v4 is installed.

THENDowngrade Zod to v3.23.8 to restore functionality, or upgrade MCP SDK to v1.23.0-beta.0 or later which adds backwards-compatible support for Zod v4. In either case, ensure the dependency version is explicitly set to avoid conflicts.

Tier 170%

version_incompatibility

ai-agents-version-incompatibil-attributeerror-module-openai-has-no-attribute-erro-06c723c1

IFAttributeError: module 'openai' has no attribute 'error' occurs when using langchain embeddings with openai version 1.0 or higher.

THENPin the openai package to version 0.28.1 by running `pip install openai==0.28.1`. Alternatively, upgrade langchain to version 0.0.330 or later, which has been updated to support the new openai v1 SDK. If you must use a modern openai version, ensure your langchain version is compatible (e.g., langchain >=0.0.330).

Tier 170%

version_incompatibility

infrastructure-version-incompatibil-running-vllm-v1-engine-in-triton-inference-server--49549e19

IFRunning vLLM V1 engine in Triton Inference Server backend fails with 'signal only works in main thread of the main interpreter'.

THENUpgrade vLLM to version 0.8.1 or later, which resolves the signal handling issue that prevented the engine from initializing outside the main thread.

Tier 170%

Connect your site → query the full pool

What you see here is the public tier-1 slice. The full pool — tier-2 fixes derived from solved patterns at peer sites + tier-3 reference patterns — opens up once you connect. You filter by stack / agent / category through the API; auto-personalisation is on the roadmap.

Connect a site

We don't publishyour competitive advantage.

Connect your site → query the full pool

We don't publish
your competitive advantage.