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

mcp_server_setup

mcp-mcp-server-setup-need-to-integrate-imagen3-image-generation-into-ch-f1b837ec

IFNeed to integrate Imagen3 image generation into Cherry Studio.

THENDownload the Imagen3-MCP executable from GitHub Releases and place it in a permanent directory. In Cherry Studio's MCP settings, set the Command field to the executable path and add the environment variable GEMINI_API_KEY with your Google Gemini API key. Optionally set BASE_URL for a proxy, SERVER_LISTEN_ADDR, SERVER_PORT, and IMAGE_RESOURCE_SERVER_ADDR for network customization.

Tier 170%

mcp_server_setup

mcp-mcp-server-setup-need-to-integrate-imagen3-image-generation-into-cu-3131fff4

IFNeed to integrate Imagen3 image generation into Cursor.

THENAdd a new MCP server entry in Cursor's configuration file (e.g., .cursor/mcp.json). Set the command to the path of the Imagen3-MCP executable and include the required GEMINI_API_KEY environment variable. Optionally add BASE_URL, SERVER_LISTEN_ADDR, SERVER_PORT, and IMAGE_RESOURCE_SERVER_ADDR for proxy or network settings.

Tier 170%

mcp_server_setup

mcp-mcp-server-setup-when-starting-with-the-agoragentic-mcp-server-for--91fa150f

IFWhen starting with the Agoragentic MCP server for use with Claude Desktop, VS Code, or Cursor.

THENRun `npx agoragentic-mcp` to start the MCP server. Optionally add `--acp` for ACP-compatible clients. The server provides the recommended tool set. No API key is needed initially; the agent can self-register via `POST /api/quickstart` later.

Tier 170%

mcp_server_setup

mcp-mcp-server-setup-you-want-to-use-hundreds-of-ai-agents-from-mcp-com-afee2593

IFYou want to use hundreds of AI site_1 from MCP-compatible clients like Claude Desktop or Cursor.

THENRun the AgentForge MCP server locally by cloning the repo, installing dependencies, setting the AGENTFORGE_API_KEY environment variable, and starting the server with `npm run mcp:start`. Then configure your MCP client (e.g., Claude Desktop) to connect to this server using stdio transport, adding the command to the mcpServers configuration.

Tier 170%

mcp_server_setup

mcp-mcp-server-setup-you-want-to-use-ruflo-s-mcp-tools-e-g-memory-store-7708d938

IFYou want to use Ruflo's MCP tools (e.g., memory_store, swarm_init) from Claude Code.

THENRegister Ruflo as an MCP server using the canonical command: `claude mcp add ruflo -- npx ruflo@latest mcp start`. This makes all Ruflo MCP tools available to Claude.

Tier 170%

mcp_server_setup

mcp-mcp-server-setup-you-want-to-access-hundreds-of-ai-agents-from-mcp--c5b0cd21

IFYou want to access hundreds of AI site_1 from MCP-compatible clients like Claude Desktop, Cursor, or Continue without manual per-agent integration.

THENRun AgentForge's built-in MCP server (mcp/server.ts) over stdio. This exposes tools like list_agents, get_agent, invoke_agent, check_agent_health, and get_platform_stats. Connect your MCP client by configuring it to execute the server with your AgentForge API key.

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.