statewright/statewright
State machine guardrails for AI agents
Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.
Appears on
Quick read
Latest capture 2026-09-19 03:04
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
1 path
Agent instructions and tool configuration found in this repository.
Agent instructions
6 observed captures since 2026-06-05. Observed captures are shown by default.
Stars from first capture +136
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
State machine guardrails for AI agents
Hindsight: Agent Memory That Learns
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
One memory, every terminal — a shared memory layer for any MCP client.
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.