DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: Meta-agent: self-improving agent harnesses from live traces
We built meta-agent: an open-source library that automatically and continuously improves agent harnesses from production traces.<p>Point it at an existing agent, a stream of unlabeled production traces, and a small labeled holdout set.<p>An LLM judge scores unlabeled production traces as they stream.<p>A proposer reads failed traces and writes one targeted harness update at a time, such as changes to prompts, hooks, tools, or subagents. The update is kept only if it improves holdout accuracy.<p>On tau-bench v3 airline, meta-agent improved holdout accuracy from 67% to 87%.<p>We open-sourced meta-agent. It currently supports Claude Agent SDK, with more frameworks coming soon.<p>Try it here: <a href="https://github.com/canvas-org/meta-agent" rel="nofollow">https://github.com/canvas-org/meta-agent</a>
Meta-agent addresses a critical bottleneck in the AI agent lifecycle—automated optimization of production harnesses—demonstrating significant performance gains on industry benchmarks like Tau-bench. While the technical innovation and market timing for agentic developer tools are excellent, the deal currently lacks commercial traction, visible funding, and detailed team background, placing it in the high-potential but very early-stage category.