heggria/Hermit
Local-first governed agent kernel for durable, inspectable, operator-trust-oriented AI work.
Implements a task-first kernel with durable execution records, policy-driven approvals before side effects, and receipt-based rollback capabilities—making agent work auditable and recoverable. Uses event-backed ledgers with hash-chain verification, artifact-native context compilation, and evidence-bound memory governance instead of transcript-only state. Targets Python 3.13+ with CLI, scheduler, webhook, and chat adapters converging on unified task/step semantics.
Stars
37
Forks
6
Language
Python
License
MIT
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/heggria/Hermit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
code-yeongyu/oh-my-openagent
omo; the best agent harness - previously oh-my-opencode
nrslib/takt
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and...
rush86999/atom
Atom Agent, automate your workflows by talking to an AI — and let it remember, search, and...
neomjs/neo
The Application Engine for the AI Era. A multi-threaded, AI-native runtime with a persistent...
beclab/Olares
Olares: An Open-Source Personal Cloud to Reclaim Your Data