Explore
MCP servers and skills: search, filter by where they run, and compare.
omnigraphModernRelay
LocalObject-storage native graph database with branching and typed ontology
SkillMIT★ 1.3kNo key
ContextLatticesheawinkler
Local
MCP servers and skills: search, filter by where they run, and compare.
Object-storage native graph database with branching and typed ontology
SkillMIT★ 1.3kNo key
The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.
SkillApache-2.0★ 154No key
O(1) prompt footprint for long-horizon agents. The SKILL.state paper (arXiv:2608.26263) reimplemented — eq. 8 reproduces exactly, 82.5x at 60 files. 100% coverage.
Node.jsMIT★ 2Few starsNo key
A reliability layer for long-running AI agents - progress survives crashes, context loss, and executor changes without relying on chat history. Ships as a normative spec, an installable agent skill, a
SkillMIT★ 3Few starsNo key
Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
SkillApache-2.0★ 368No key
Stand up Grafana Mimir for horizontally scalable, multi-tenant, long-term Prometheus + OTLP metrics storage. Covers monolithic / read-write / microservices deployment, S3 / GCS / Azure / filesystem bl
OfficialSkillApache-2.0★ 285 in collectionNo key
Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eage
Node.jsMIT★ 501No key
Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.
PythonMIT★ 15No key
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
SkillMIT★ 293No key
A Codex Agent Skill for long-horizon reasoning, context synthesis, root-cause persistence, verification, and completion discipline.
SkillMIT★ 8No key
An open, thin, model-agnostic harness for long-horizon autonomous AI research. Built on Goose.
SkillApache-2.0★ 13No key
Structured context management framework for LLM agents. Implements Git-like operations (COMMIT, BRANCH, MERGE) to manage long-horizon agent memory.
SkillMIT★ 63No key
Industrial benchmark for AI memory – measuring how accurately LLM and agent memory systems recall long-term context, with uniform, reproducible scoring across datasets and memory products.
SkillApache-2.0★ 9No key
A Git-backed, agent-readable workspace for durable knowledge and long-horizon work.
SkillMIT★ 3Few starsNo key
A semantic, transactional, replayable MCP control plane that lets autonomous AI agents operate Dwarf Fortress as a long-lived civilization. Safe-Rust phase-0B scaffold: MVCC world state, witnessed sem
SkillMIT★ 23No key
Security-first agent harness built for long horizon research and work capabilities with increased focus on math, computer science, and domain science research
SkillApache-2.0★ 4Few starsNo key
Cognitive Operating System for AI Agent (Skill.md) Self-thinking Multi-agent reasoning Meta-cognition Self-evolution
SkillApache-2.0★ 15No key
Open-source SuiteCRM MCP server. Connect Claude Desktop, Claude Code, or any AI agent to SuiteCRM in under 5 minutes. OAuth2/OIDC, 24 tools, full observability.
Node.jsMIT★ 1Few starsNo key
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effe
SkillMIT★ 18kNo key
A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with
SkillMIT★ 158No key
Who stands behind it
