Track and replay AI agent execution states, checkpoint progress, and undo actions for debugging and recovery. Built for developers who need deterministic agent behavior testing and state management.
io.github.charo360/statecli
Local install
STDIO
No auth required
How models use it and what it is built for.
Track and replay AI agent execution states, checkpoint progress, and undo actions for debugging and recovery. Built for developers who need deterministic agent behavior testing and state management.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Charo360 Statecli.
Paste any of these into Agent Studio after connecting Charo360 Statecli.
Common questions about connecting and running Charo360 Statecli.
What does state replay mean for AI agents?
State replay lets you restore an agent to a previous execution point and re-run from there, useful for debugging failures or testing alternate paths. Combined with checkpointing, you can save known-good states and return to them instantly.
How do I install and start using statecli?
Install via `npx statecli-mcp-server@0.5.0` and connect it to your MCP client. The server communicates over stdio, so it integrates with any MCP-compatible tool or agent framework.
Can I undo agent actions and try a different path?
Yes. The undo feature lets you roll back agent steps, then checkpoint the new state or replay from an earlier point to explore alternative execution branches.
What's the difference between checkpoint and replay?
A checkpoint saves the current agent state as a named snapshot. Replay restores a previous checkpoint and re-executes from that point, letting you test determinism or debug specific sequences.
Is statecli suitable for production agent monitoring?
Statecli is designed for development, testing, and debugging workflows. Check the project documentation for guidance on production use cases and state storage limits.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams