Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Self-hosted Docker stack for cross-platform AI agent rooms (Claude Code + ChatGPT + any LLM). MIT.
SkillMIT★ 1Few starsNo key
Claude Code plugin: capture your cognitive signature across code, writing, design, any creative domain — inject it into Claude's output so it matches your voice. Multi-agent governance via Managed Age
SkillMIT★ 2Few starsNo key
Cognitive architecture for AI agents. 19+ skills that force language models past surface-level reasoning into genuine depth. Compatible with Claude Code, Cursor, Gemini CLI, Copilot, and any agent tha
SkillMIT★ 5No key
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapp
PythonApache-2.0★ 480No key
Adaptive extractive text compression for AI agents. Shorten academic documents without paraphrasing, with traceable edits, semantic review and optional lightweight OCR.
SkillMIT★ 10No key
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based conso
PythonMIT★ 75No key
Booster MCP is an MCP server for semantic code analysis, repository mapping, and large codebase navigation. This release prepares the project for public use with a cleaner package identity, bundled ag
PythonMITFew starsNo key
Titan-Memory , it is a memory system that is not only for memory, but it also has built-in safety guardrails, circuit-breakers, semantic adapters, and drift protection. Everything you need to run Agen
Node.jsApache-2.0★ 5No key
Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQL
PythonMIT★ 61No key
PythonMIT★ 7No key
Give your AI agents a brain that gets smarter over time. 6-tier memory hierarchy with hybrid search, background consolidation, confidence decay, and cross-agent knowledge promotion. Ships with CLI, MC
PythonMIT★ 7No key
git for agent brains — move, debug, and secure AI agent state across 10 frameworks
PythonApache-2.0★ 8No key
🚀 Enterprise Multi-Agent Operating Framework: 404 curated production skills & 120 specialized subagents for Antigravity, Claude, and Codex with 70% token compression.
SkillMIT★ 2Few starsNo key
An agentic scriptorium for scholarly writing — coordinated AI capabilities for manuscripts, grants, and reviews.
SkillMIT★ 5No key
Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says "steno mode", "shorthand mode", "compressed respo
OfficialSkillMIT★ 40k in collectionNo key
Universal Git-powered persistent memory, context rules & native MCP server for AI coding agents. Prevents context amnesia with stateful workflows, Git Notes, and cross-model review gates across Claude
Node.jsMIT★ 4Few starsNo key
Tool-agnostic AI agent memory as a local-first Rust CLI: cognitive verbs (remember, recall, learn, consolidate, forget), plain-markdown memories, local candle embeddings, and HNSW semantic search acro
SkillApache-2.0★ 4Few starsNo key
Self-hosted LLM cost observability and trajectory compression. 43-45% token reduction on coding agents. Python SDK · MCP server · Proxy · Grafana dashboards.
SkillMIT★ 3Few starsNo key
Claude Code plugin marketplace — discover and install skills, commands, and agent configurations
SkillApache-2.0★ 2Few starsNo key
Refactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by extracting helper methods.
OfficialSkillMIT★ 40k in collectionNo key
Assembly for LLM Agents. High-density notation for flow-state vibe coding.
SkillMIT★ 3Few starsNo key
Persistent semantic memory for Claude Code. Three-layer wiki + LanceDB vectors, hooks, self-healing lint, knowledge graph. Native MCP integration.
SkillAGPL-3.0★ 1Few starsNo key
The methodology layer for Claude Code — 99 first-party working methods across 10 behavioral plugins. Better methods, not just more data.
DockerMITFew starsNo key
Smart Promise Tracker AI 2026 – Commit Memory Engine
MCPLink only★ 136
Who stands behind it