AI & Agents MCP servers

Persistent knowledge graph and MCP server for AI workflows with git-tracked project context.

Local-first governed MCP memory backend for coding agents.

Universal AI skill compiler and MCP bridge. Write once, run across agents.

Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.

Provenance-aware memory format for AI agents: every claim carries its source, age and boundary.

Lets AI coding agents coordinate asynchronously through a private git repository. No server.

Secure Linux sandboxes for AI agents, as MCP tools.

Local Redis memory MCP for AI apps with hybrid caching and optional Mem0 cloud backup.

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs.

Route MCP capabilities through deterministic identity, policy, budget, and deadline constraints.

Records MCP tool calls and itemises the token cost each server adds to your context.

Reference MCP server for OCL, an open standard giving AI agents scoped business meaning for Odoo.

Local profiler: which usage window took you out, and where your agent's money goes

Local MCP broker that exposes one compact entry for many upstream servers.

Local-first agent memory. Source, date, bind/abstain. Permanent name: lbrain.ai/claim.html

Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.

Coherence guard for shared files: denies stale writes so agents don't silently overwrite each other.

Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.

Capture tool workflows, save typed tools, and replay with human approval. Includes an MCP Apps UI.

Task-to-tool discovery over the merged x402 Bazaar + MCP Registry catalog

Self-curating agent memory kept honest by survival-based selection over measured outcomes.

Universal MCP gateway with Meta-MCP discovery, routing, and REST API capabilities.

Human approval for AI agents: a named person approves or rejects, silence is not consent.

Free seven-tool proof loop for scoped authorization, outcome receipts, and evidence-bound claims.

Wraps local Ollama models so bulk generation runs on your own hardware, not a paid API.

Review-gated declarative long-term memory with bounded read-only MCP access.

Search 344 human-reviewed AI/agent repos and the 817 typed connections between them.