AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
Self-hostable AI agent platform with sandboxed tool execution and multi-tenant governance
AI summary · README
Developer toolsPython · HTMLGitHub @15838328874Self-installOwner unconfirmed
Paste into Claude or ChatGPT for installation instructions suited to your environment.
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Installable projects can be verified without a deployment domain. Use GitHub sign-in for a personal repository, or the repository verification file above for an organization repository.
Ask about other verification options
Loading the full README. The saved excerpt is shown below.
A self-hostable, extensible AI agent platform: sandboxed tool execution, multi-tenant
governance (JWT/quotas/rate limits/audit), a canonical trajectory log, an eval harness with
scoring and A/B, an RL data flywheel (rollout→reward→SFT/RLVR JSONL), and protocol-level
tool extensibility via MCP + Skills. Coding is the first fully-developed scenario, not the
boundary. Python reimplementation of the pi coding agent
harness, shipped as a multi-user HTTP service: streaming LLM layer, asyncio agent loop, coding
tools, and sandboxing (CubeSandbox microVMs in production, Docker locally).Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
A self-hostable, extensible AI agent platform: sandboxed tool execution, multi-tenant
governance (JWT/quotas/rate limits/audit), a canonical trajectory log, an eval harness with
scoring and A/B, an RL data flywheel (rollout→reward→SFT/RLVR JSONL), and protocol-level
tool extensibility via MCP + Skills. Coding is the first fully-developed scenario, not the
boundary. Python reimplementation of the pi coding agent
harness, shipped as a multi-user HTTP service: streaming LLM layer, asyncio agent loop, coding
tools, and sandboxing (CubeSandbox microVMs in production, Docker locally).Read the full README ↗