About lrsi
LRSI is a local autonomous agentic operating system for teams building and governing agent workflows. It routes every mutation through a fail-closed boundary and records an append-only audit trail.
Key features
- 01Fail-closed mutation boundary
- 02Append-only event audit trail
- 03Evidence-gated promotion
- 04CLI, SDK, REST API and MCP
- 05Multi-agent workflow surfaces
Use cases
- 01Gate agent-initiated system changes
- 02Audit workflow mutations
- 03Promote changes after evidence review
MCP support
The `lrsi-mcp` server exposes LRSI through MCP. Mutations are governed by the fail-closed boundary and recorded in the event trail.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMELRSI
LRSI (Local Recursive Self-Improvement) — Autonomous Agentic Operating System
Sovereign, closed-loop system on dual Blackwell hardware. Built on the open LRSI Runtime Core (marcuszimmermann365/IRSI). Every mutation is forced through a fail-closed boundary and append-only event trail.
Support Agentic OS Kernels ($99) · Agentic OS Cycle ($0.75) · Public Goods Support
Non-custodial USDC (preferred for agents)
| Network | Address |
|---|---|
| Base / Ethereum | 0xD3d0E9eDAe3Ac7bb199a8EAA761BdA423b878438 |
| Solana | ETQwWf19axArsY493UfC6bxe2BmEzmzvCb58PPnC38A |
Related: rui · server-os · openmesha · OpenGOS
Surfaces
| Surface | Entry |
|---|---|
| CLI | lrsi status / lrsi workflow / lrsi mutate / lrsi audit |
| SDK | from lrsi.sdk import LRSIClient |
| REST API | lrsi-api → http://localhost:8080/docs |
| MCP Server | lrsi-mcp |
| Multi-agent | improver → evaluator → council + skills/multi-agent-workflow/ |
| CI | .github/workflows/ci.yml |
| Verify | bash scripts/verify.sh |
Quick Start
pip install -e ".[dev,mcp,api]"
bash scripts/verify.sh
lrsi-api
Design principles
- Fail closed
- Every mutation through the LRSI boundary
- Event-sourced audit trail
- Evidence-gated promotion
- Multi-surface (CLI · SDK · API · MCP · workflows)
License
Apache-2.0
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.