MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Project memory for Codex and Antigravity, with DSH support on main. Local work history, bounded knowledge injection, progressive retrieval, explicit history import, a visual knowledge browser and opti
PythonMIT★ 1Few starsNo key
Shared, brain-inspired memory for AI agents: 13 brain regions with awake/sleep loops, a live visualizer, agents connected via REST/SDK/MCP, governance & audit, and business-value metrics. Works with C
SkillMIT★ 5No key
Open public broadcast and durable shared memory for AI systems and agents — signed Events, discovery, relays, and independent Nodes.
PythonMIT★ 1Few starsNo key
Opinionated agent skills for shipping production apps on Next.js, FastAPI, PostgreSQL, Expo, and SwiftUI.
SkillMIT★ 4Few starsNo key
Shared brain for your AI agents: self-hosted knowledge + task backbone for Claude, ChatGPT & any MCP client. Git-versioned Markdown, atomic task claims, ACL, audit. Zero dependencies.
DockerAGPL-3.0Few starsNo key
Per-person attention budgets for AI agents and background automations: agent budgets, quiet hours in each person's time zone, digests and human approval in front of every agent. Self-hosted, Postgres
PythonMIT★ 1Few starsNeeds a key
Shared local memory for Claude Code, Cursor, and Codex that stays true to your code.
PythonMIT★ 2Few starsNo key
Cybersecurity for AI founders and vibe coders. A pre-push security gate for apps built with Claude Code, Cursor, Lovable and Bolt.
Node.jsMITFew starsNo key
AI agents that find money-laundering rings no single bank can see, on FalkorDB: one graph per bank, a consortium graph, echo-proof evidence, signed reports and a hosted MCP server.
Hosted by authorMITFew starsNo key
Persistent, local-first developer environment: GUI-grade terminal, persistent sessions, searchable history, and an API/MCP interface for external AI agents.
SkillMIT★ 9No key
Authorization for Postgres apps: access rules in a policy file, compiled to row-level security. Sharing, groups, nested folders, tenants; no second service.
Node.jsApache-2.0★ 2Few starsNo key
Read-only MCP server that gives AI agents safe access to your databases: PostgreSQL, MySQL/MariaDB, ClickHouse, Oracle, SQL Server, Db2 and SQLite
DockerApache-2.0Few starsNo key
In-memory graph database and Gremlin traversal engine in Rust: browser playground, CLI, MCP server for AI agents, durable store, Python bindings.
SkillApache-2.0★ 15No key
Build-time permission checker for TypeScript and AI agents: fails the PR when code adds a new server, file, secret, database table, risky MCP tool, or CI permission.
Node.jsApache-2.0★ 1Few starsNo key
SQL query, migration and plan analysis for AI agents (MCP server)
Node.jsMITFew starsNo key
Lightweight self-hosted RAG knowledge base: Spring Boot 4 + Spring AI, SQLite/FTS5, hybrid retrieval with RRF, cited answers, MCP server
Hosted by authorMITFew starsNo key
Read-only Postgres MCP server: a drop-in replacement for the archived server-postgres, with schema context for correct answers.
Node.jsMIT★ 4Few starsNo key
Preflight safety checks for TypeORM migrations: catch data loss and locking before you merge.
Node.jsMITFew starsNo key
Public MCP surface of an autonomous AI agent shop: server card, live tool schemas, and a zero-dep parity check that fails on drift.
Hosted by authorMITFew starsNo key
Local automation service for recurring and one-off background script tasks, with a CLI, a Flask Web UI and an agent skill
SkillLink only★ 3Few stars
Your agents, briefed. Not flooded. Self-hosted context compiler: git-backed team knowledge served to coding agents as token-budgeted bundles over MCP.
DockerApache-2.0★ 31Needs a key
Who stands behind it
