AI & Agents MCP servers

Read and write Claude Code auto memory from Codex, Cursor or any MCP client. Zero dependencies.

Tells your agent which model to use and what it costs, across 46 providers and local runtimes.

Accountable autonomy proxy: gating, tamper-evident audit, time anchor for every action

Local procedural knowledge with spells, notes, and revision history.

One MCP endpoint for all your servers: a few meta-tools, Keychain secrets, sandbox, audit, OAuth.

Local-first memory over MCP. Built-in SQLite store; runs standalone. Agents propose; you confirm.

Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.

Cryptographic Merkle tree verification engine for agent state transitions, tool call histories, and

Curated MCP tools from OpenAPI, websites, apps, Postman, cURL or SQL; your agent designs them.

Shared local memory for AI coding tools that stays true to your code.

Public source-linked memories for AI agents: search, read, cite, reply, and share findings.

Multi-provider Pi agent teams: parallel delegates, coordination, steering, optional recovery.

Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor

Let a planning agent hand bounded language work to a local Ollama model.

Chinese frontier AI models as MCP tools via one OpenAI-compatible endpoint, zero platform fee.

A host-agnostic MCP worker runtime for supervising local Pi coding-agent processes.

Governed tacit memory for AI agents: reviewed expert know-how, given only where conditions match

ToolDrift: Current AI model pricing and which models coding tools route to.

Self-hosted memory for LLMs in TriliumNext, structured by the server and editable by you.

deja-vu: local memory over the session histories of forty-three coding agents.

Token-light local memory with SQLite hybrid retrieval for MCP agents.

Gives your agent the right public skill for each task and loads it on demand.

Reliability scoring for agent jobs and habit analytics. Pay per call via x402 (USDC on Base).

Free-to-start portable memory for AI agents: encrypted, shareable, provably erased. Join SAIHM.

Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.

Your PromptLikeEngineer prompt library as MCP tools, slash prompts and resources. Add-only saves.

Curated, on-demand memory for AI coding agents. Cuts Claude Code token cost per session.

Developer memory CLI and MCP server. Remember decisions, preferences, and lessons locally.