Run many AIs on one board and keep control of all of it. Deterministic code decides who acts — never a model. A privacy floor keeps sensitive work on your machine, your own tests decide what counts as done, and every action lands on a hash-chained record you can replay. Free, macOS today; cross-platform and teams next.
Source
GitHub
Dernière activité
3 sept. 2026
Étoiles1Mesuré · 21 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative
A local A2A event and continuity service for agent applications, with structured history, provenance-safe transcripts, literal search, and natural-language queries.
Source
GitHub
Langage
Python
Dernière activité
2 juil. 2026
Étoiles1Mesuré · 21 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative
Accountability layer for AI agents: run the client's executable acceptance tests, gate delivery, sign every step into a verifiable receipt. Pre-registered, replicated 5x, cross-benchmark.
Source
GitHub
Langage
Python
Dernière activité
13 oct. 2026
Étoiles1Mesuré · 21 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative
Local-first Agentic AI Infrastructure Platform with LLM Gateway, Agent DAG Runtime, MCP Tool Hub, A2A Agent Mesh, Local RAG, Tool Sandbox and Observability.
Source
GitHub
Langage
Python
Dernière activité
21 oct. 2026
Étoiles1Mesuré · 21 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative