Meta-agent: self-improving agent harnesses from live traces
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
We built meta-agent: an open-source library that automatically and continuously improves agent harnesses from production traces.Point it at an existing agent, a stream of unlabeled production traces, and a small labeled holdout set.An LLM judge scores unlabeled production traces as they stream.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.On tau-bench v3 airline, meta-agent improved holdout accuracy from 67% to 87%.We open-sourced meta-agent. It currently supports Claude Agent SDK, with more frameworks coming soon.Try it here: https://github.com/canvas-org/meta-agent
HN · launched Apr 6, 2026 · 14 upvotes (top 31%) · 0 views
Niche: ai agent development platforms · 598 launches, 22 in the last 7 days ▼ -29% · Explore this niche →
Category and tags
- Horizontal
- Agent / copilot
- Developer
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 598 launches in ai agent development platforms →
Could you build this?
Partial The basic framework of tracing prompts and feeding outputs to an LLM judge is approachable, but building an automated optimizer that continuously refines agent harnesses without regressing requires complex evaluation pipelines and prompt optimization theory.
What it would actually take: The system requires a distributed tracing and observability pipeline (OpenTelemetry, ClickHouse/PostgreSQL), an automated LLM-as-a-judge scoring harness, and an iterative optimization engine using algorithms like DSPy or GEPO (Genetic Prompt Optimization). The hard problem is preventing reward hacking, managing prompt drift, and maintaining statistical rigor across agent harness mutations without human-in-the-loop validation, requiring specialized AI evaluation engineering.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one : 1958 launches clear the similarity bar, closest 8 shown.
Attention rank: #645 of 1959 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 159 days after the earliest competitor.
- agent-harness · github · 2026-10-09 · 11 upvotes · similarity 0.52
- octop-harness · github · 2026-09-24 · 17 upvotes · similarity 0.52
- Moda: The Continual Learning Layer for AI Agents · yc · 2026-03-04 · 122 upvotes · similarity 0.52
- I built an open source multi-agent harness in Go · hn · 2026-04-08 · 6 upvotes · similarity 0.52
- agent-flow · github · 2026-09-26 · 10 upvotes · similarity 0.51
- Harness² · ph · 2026-10-20 · 167 upvotes · similarity 0.51
- Coordination Layer for Coding Agents · hn · 2026-08-28 · 9 upvotes · similarity 0.50
- Gambit, an open-source agent harness for building reliable AI agents · hn · 2026-01-16 · 91 upvotes · similarity 0.50
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.