Knowledge & Memory

ClawSouls MCP Server — SoulScan, Soul Rollback, Swarm Memory, Persona Search & Install for AI agents

sox-memory MCP server (stdio/http/sse) — 23 memory_* tools over a Turso (default, multiprocess-write) or SQLite graph store, with hybrid recall and deterministic in-process enrichment

Git-native context layer for AI coding agents: scan a repository into a structured, versionable .agent/ knowledge layer and query it (CLI + programmatic API).

MCP server fronting the Miadi voice layer with episode addressing — play, find, publish and mint episode-bound voice from an agent's tool surface.

LCV-branded MCP reasoning gate for structured engineering thought, validation, and review readiness.

One private, local memory your AI tools share. Cross-model, on-device, never lose a session.

MCP server for AgentPlanner — AI agent orchestration with planning, dependencies, knowledge graphs, and human oversight

Cross-session memory for AI coding agents via six tools; local-first SQLite store.

MCP server and CLI for Spector — Cognitive memory engine for AI agents

A screen ↔ endpoint ↔ field dependency map: answers which screens break if you change an endpoint or a response field. Local-first, git-friendly, open source.

Read Microsoft Teams teams, channels, chats and messages, and post/reply/send, safe by default.

MCP Server for oh-memos — Intelligent Memory Management (Node.js, no Python required)

Structural code intelligence for DeepSeek Harness — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, what a change reaches, and how one symbol reaches another, from a tree-sitter index it builds itself

Check a site before you share it: link previews, SPA refresh 404s, noindex, security headers.

Memory, discovery and knowledge for AI agents — x402 pay-per-call on minia2a. Find the right service for a task (semantic search over 1,600+ x402 APIs), recall agent-economy knowledge, persist state across calls, search the web. No API keys, no subscripti

AI 数据库接入扩展 for pi coding agent：PostgreSQL/MySQL/Oracle/达梦DM/Redis/Elasticsearch/MongoDB/Neo4j/Hive/Spark 十种数据库，查询/表结构/扫描建连/安全管控 | Database tools for the pi agent: query, schema, scan-and-connect for 10 databases

Vault-first persistent memory for AI coding agents, with an optional profile-aware governance runtime: OFF, FLOW, GUIDE, GOVERN, or ASSURE. Local-first and agent-agnostic (Claude Code, Codex, Cursor…).

relay: your coding-agent subscriptions (Claude Code, Codex, Grok) as one system. The CLI, the session hooks and the memory MCP server.

Agent Cairn server: MCP endpoint, JSON API and dashboard for shared agent memory.

Capability graph of your agent stack: what it can do, what to set up next, what breaks.