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_integration

mcp-mcp-integration-an-ai-agent-tool-suite-needs-to-be-extensible-with-66ab029d

IFAn AI agent tool suite needs to be extensible with external services (e.g., databases, APIs, custom tools) using a standardized protocol.

THENIntegrate the Model Context Protocol (MCP) to connect to MCP servers as additional tool providers. The agent can discover and call tools from multiple MCP servers, with a health chip in the UI showing connectivity status (e.g., 'MCP n/n' glyph in footer). Server configuration can be done via config files.

Tier 170%

mcp_integration

mcp-mcp-integration-developer-wants-to-use-ateam-mcp-with-claude-deskt-21f10ce8

IFDeveloper wants to use ateam-mcp with Claude Desktop.

THENAdd the MCP server configuration to claude_desktop_config.json with command 'npx -y @ateam-ai/mcp' and environment variables ADAS_TENANT and ADAS_API_KEY.

Tier 170%

mcp_integration

mcp-mcp-integration-need-to-equip-an-agent-with-external-tools-via-the-a58c37d7

IFNeed to equip an agent with external tools via the Model Context Protocol (e.g., web browsing, code execution).

THENInstall @playwright/mcp npm package, then use StdioServerParams and McpWorkbench in AutoGen to attach MCP tools. Set max_tool_iterations to limit tool calls. Use agent.run_stream for streaming output.

Tier 170%

mcp_integration

mcp-mcp-integration-developer-wants-to-add-ateam-mcp-to-claude-code-b29dd6a4

IFDeveloper wants to add ateam-mcp to Claude Code.

THENRun the command 'claude mcp add ateam -- npx -y @ateam-ai/mcp' in the terminal.

Tier 170%

mcp_integration

mcp-mcp-integration-developer-wants-to-integrate-ateam-mcp-with-cursor-3e5c03be

IFDeveloper wants to integrate ateam-mcp with Cursor, Windsurf, or VS Code Copilot.

THENAdd the same MCP server configuration to the respective MCP configuration file (.cursor/mcp.json, mcp_config.json, .vscode/mcp.json) with the same command and environment variables.

Tier 170%

mcp_integration

mcp-mcp-integration-need-to-create-a-web-browsing-assistant-agent-usin-9468d5c9

IFNeed to create a web browsing assistant agent using the Playwright MCP server.

THENInstall the Playwright MCP server globally via npm, then use `McpWorkbench` and `StdioServerParams` to connect to it. Create an `AssistantAgent` with the workbench parameter for tool access.

Tier 170%

mcp_integration

mcp-mcp-integration-need-to-extend-gemini-cli-with-custom-tools-e-g-gi-470e0b3e

IFNeed to extend Gemini CLI with custom tools (e.g., GitHub, Slack, database queries)

THENConfigure MCP servers in ~/.gemini/settings.json with server name, command, and args. Use '@server-name' in prompts to invoke the custom tool.

Tier 170%

mcp_integration

mcp-mcp-integration-need-to-integrate-mcp-tools-e-g-playwright-for-web-70b7317c

IFNeed to integrate MCP tools (e.g., Playwright) for web browsing in an agent.

THENInstall @playwright/mcp, then use StdioServerParams and McpWorkbench to provide tools to an AssistantAgent. Pass the workbench to the agent and call run_stream.

Tier 170%

mcp_integration

ai-agents-mcp-integration-user-wants-their-ai-assistant-claude-cursor-windsu-1d78acbb

IFUser wants their AI assistant (Claude, Cursor, Windsurf) to discover and pay other site_1 for capabilities.

THENRun `npx @elisym/mcp init` to create an agent configuration, then `npx @elisym/mcp install --agent <agent-name>` to register tools, then restart the MCP client to gain agent discovery and purchase tools.

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.