📡 MCP Radar

gatordevin/avo

Open reproduction of NVIDIA's AVO paper (arXiv:2603.24517): evolutionary search where an autonomous coding agent IS the variation operator — Vary(P)=Agent(P,K,f). Runs on the Claude Code or Codex sess

⭐ 3 stars
⑂ 1 forks
Python
momentum ▲ 7.0
created 2026-08-22
on radar since 2026-08-26
2048claude-codecodexcoding-agentsevolutionary-algorithmsexpectimaxkernel-optimizationllm-agentsmcpmcp-serverpaper-implementationreproducibility
View on GitHub ↗

About avo

An open reproduction of AVO: Agentic Variation Operators for Autonomous Evolutionary Search (Chen, Ye, Xu et al., NVIDIA, 2026), runnable on a laptop.

Classical evolutionary search, and the LLM-augmented systems that followed it, decompose the variation operator into a fixed pipeline:

The framework samples parents; the model produces one candidate from them. AVO replaces that whole decomposition with a single autonomous agent run:

The agent sees the full lineage Pt, a domain knowledge base K, and the scoring function f — and decides for itself what to read, what to change, and when to measure. It stops being a candidate generator and becomes the variation operator.

This repo implements that framework, plus the surrounding machinery the paper describes: a git-backed lineage, a correctness-gated score vector, the matches-or-improves commit policy, a supervisor that intervenes on stagnation, and trajectory plots. Two optimisation targets ship with it.

The part that matters: it runs on the session you already have

The default driver does not spawn an agent and does not call an API. It hands the variation prompt to the Claude Code session you are already talking to, and that session does the work. Nothing extra is billed, no ANTHROPICAPIKEY is needed, and the agent doing the optimising is a real general-purpose coding agent — which is exactly what the paper used.

Unattended mode (spawn an agent per step and let it run for days, like the paper's 7-day experiment) is available too, and is opt-in precisely because it spends quota.

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/gatordevin--avo.html)

Related MCP servers

zriyox/codex-supervisor-mcp

Codex MCP server: run parallel Codex CLI workers in isolated git worktrees, state on disk, web dashboard, auto-update.

⭐ 3JavaScript
dongnguyenvie/bashcut-agent-kit

BashCut's agent kit: editing skills (footage survey, beat cuts, audio mix, captions, colour, voiceover…) and the BashCut MCP server for Claude Code and Codex.

⭐ 5Python
vshulcz/deja-vu

Your agents already solved this. deja finds it — retroactive search and MCP recall over the session logs your coding agents already wrote. Cross-agent, SSH-portable, one zero-dep binary, fully local.

⭐ 391Go
dongnguyenvie/BashCut

Native macOS video editor that coding agents can drive: everything the UI does, Claude Code and Codex can do through the bashcut CLI or MCP server. Layered timeline, captions, voiceover, plugins.

⭐ 55Swift
lordfine/codex-claude-bridge

Codex ↔ Claude Code MCP bridge for AI agent orchestration: task delegation, event-driven handoffs, reasoning profiles and evidence reuse. Windows/macOS; optional Orca.|Codex 指挥 Claude Code:会话管理、阶段交付与验

⭐ 6JavaScript
magna-nz/tallybook

Prices your Claude Code and Codex sessions from the transcripts on disk, shows what each agent cost over any period, and tells you in plain English what would have been cheaper. CLI, Browser UI and MC

⭐ 5Go

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.