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.
Package manager for things. Start designing modular hardware! PartCAD is the standard for documenting manufacturable physical products (a.k.a. Digital Thread or TDP). It comes with a set of tools to m
PythonApache-2.0★ 509No key
Self-hosted event engine for any mailbox: IMAP, JMAP and inbound SMTP in, one replayable event log out, with safe reversible actions, scoped tokens for AI agents, and an MCP server.
SkillApache-2.0★ 8No key
Portable Relational Memory Engine — local-first memory substrate for LLM-powered systems
PythonApache-2.0★ 3Few starsNo key
An open agent-skills library for malware analysis, reverse engineering, and threat hunting - 118 curated, runnable skills mapped to MITRE ATT&CK, D3FEND, and CAR.
SkillApache-2.0★ 22No key
Continuity, causal invalidation, and proof for long-running coding agents
PythonApache-2.0★ 1Few starsNo key
AI-native event store — 469K events/sec ingest, 11.9µs p99 indexed reads, 55 default MCP tools (73 with admin).
SkillApache-2.0★ 3Few starsNo key
Where knowledge flows, voices follow.
Node.jsApache-2.0★ 1Few starsNo key
An open engine for company-wide LLM agent automation. Agents work inside a signed remit, stop at the policy gates you set, and keep running unattended for months.
SkillApache-2.0★ 1Few starsNo key
MCP server and EasyEDA Pro bridge for AI-assisted PCB review, component sourcing, manufacturing export, and JLCPCB ordering workflows.
Node.jsApache-2.0★ 4Few starsNo key
Deterministic hierarchical statechart engine with a tamper-evident journal and exact decimal arithmetic. Zero dependencies. Usable as a Rust library, a CLI, or an MCP server for LLM-driven workflows.
SkillApache-2.0Few starsNo key
The open ontology store. Every value typed, traced and verifiable: an ontology types every write, every field keeps its source and time, a hash-chained log anyone can check. Local MCP, Apache-2.0. The
SkillApache-2.0Few starsNo key
Auditable memory for AI agents — provable deletion (crypto-shred + signed certificate), a tamper-evident audit chain, and bi-temporal time-travel recall. Runs on SQLite or Postgres.
PythonApache-2.0Few starsNo key
The open, governed state layer for AI agents — trustworthy, not smarter. The model proposes; a deterministic engine decides; every change is an event. Sits under any agent framework, MCP-compatible.
SkillApache-2.0★ 1Few starsNo key
Who stands behind it