HuggingFace open-sources ipython-harness: a minimal ipython-only agent eval framework
yb2698 · x · 2026-10-14
The companion repo ipython-harness is now open source: a minimal, experimental agentic harness built purely on ipython for evaluation and benchmarking. It works with any OpenAI-compatible server (the example runs Qwen3.5-9B via llama-server) and includes example.py where the agent analyzes a codebase and writes a README. The author thanks community reviewers and invites others to build on it.
More from coding & agent
- Google's ADK brings one agent framework to Python, Go, TypeScript, Java and Kotlin — rseroter · 2026-10-15
- AI agent flags a bizarre '71 >= 71' error while a server pool balloons by 1.4TB — haydendevs · 2026-10-15
- Invideo launches an MCP for editing videos directly via Claude or ChatGPT — azed_ai · 2026-10-15
- Connecting Grok to ROS via OpenClaw and AgenticROS for robotics missions — chrismatthieu · 2026-10-15
- Automating bug report fixes: a Bot triages DMs into a Cursor project — msfeldstein · 2026-10-15
- Devin now auto-fixes Pylon support tickets; new customers get $15,000 in credits — DevinAI · 2026-10-15