Explore
MCP servers and skills: search, filter by where they run, and compare.
handoffstoneyunusarda-sudo
LocalPortable, verifiable, decision-aware context handoffs for AI agents.
PythonApache-2.0★ 1Few starsNo key
intagrinintagrin
MCP servers and skills: search, filter by where they run, and compare.
Portable, verifiable, decision-aware context handoffs for AI agents.
PythonApache-2.0★ 1Few starsNo key
IntaGrin is a declarative framework for building multi-agent LLM systems. Instead of wiring routing logic in Python (as you would with a hand-built graph), you describe agents, handoffs, tools, and gu
PythonApache-2.0★ 1Few starsNo key
OCTAVE protocol - structured AI communication with 3-20x token reduction. MCP server with lenient-to-canonical pipeline and schema validation.
PythonApache-2.0★ 54No key
MCP server for client-encrypted AI agent handoffs with WorkBaton and WorkStash
PythonApache-2.0★ 2Few starsNo key
Experimental capacity-aware cognitive compression for AI agents — compile large context, evidence, constraints, and procedures into small-model-ready packages with provenance and fidelity checks.
SkillApache-2.0Few starsNo key
Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
PythonApache-2.0★ 6Needs a key
Local multi-agent workspace with Hermes orchestration, role-based AI agents, memory, scheduling, Skills, MCP, terminal, files, and HTML preview.
PythonMIT★ 5No key
Delegate tasks to DeepSeek right inside your Claude Code / Codex sessions.
SkillLink only★ 95
Persistent memory graph for AI coding agents — semantic search, knowledge graph, and time-based decay over MCP
PythonMIT★ 5No key
Turn before/after time-series questions into counterfactual charts, reproducible reports, share packages, and AI-agent-ready handoffs.
PythonMIT★ 3Few starsNo key
Python engine and agent skill for evidence-backed claim graphs, uncertainty, assessments, recovery, and tamper-evident ledgers, with Spec Kit integration.
SkillMIT★ 1Few starsNo key
The Bi-Temporal State Graph & Lossless Context Compression Engine for AI Agents
PythonApache-2.0★ 1Few starsNo key
Local-first issue deck for humans and AI coding agents: dashboard, MCP tools, SQLite, and CSV/JSON/Markdown imports.
PythonMIT★ 2Few starsNo key
A clean, modular framework for building AI agents with Claude, featuring MCP integration, web search capabilities, and Google Drive integration
PythonMIT★ 1Few starsNo key
NeuroMem is a memory middleware layer that sits between your client and an upstream model. It retrieves session-scoped memories, injects them as structured context, stores the new turn, and returns th
PythonGPL-3.0★ 1Few starsNo key
Personal memory system for AI coding agents. Offline, zero API keys, cross-agent handoffs, semantic search. Works with Claude Code, OpenCode, Codex, Cursor & more.
MCPLink only★ 1Few stars
Multi-session collaboration for Claude Code: atomic locks, handoffs, memory graph, messaging, hub server, bridge, voice I/O. 166 tests. Zero core deps.
PythonMIT★ 7No key
Remembra Relay: one agent stops, the next one already knows. Session handoffs built from git facts, for the next coding agent in any MCP tool, on any machine. MCP server + CLI. MIT.
PythonMIT★ 16No key
An evaluation suite for AI agent skill triggering and collision detection
OfficialSkillApache-2.0★ 13No key
Cross-session memory for Claude Code — MCP server for context handoffs
SkillMIT★ 7No key
Shared memory, focused engineering practices and reliable handoffs for coding agents. Give your agent one setup prompt.
SkillMIT★ 5No key
Portable, local-first context handoffs for AI coding agents
PythonMITFew starsNo key
Who stands behind it
