LLM agents that write Python to analyze execution traces at scale
We combined Stanford's ACE (agents learning from execution feedback) with the Reflective Language Model pattern. Instead of reading traces in a single pass, an LLM writes and runs Python in a sandbox to programmatically explore them - finding cross-trace patterns that single-pass analysis misses. The framework achieved 2x consistency improvement on τ2-bench.
LLM agents that write Python to analyze execution traces at scale launched on March 7, 2026 with 5 votes, #1,928 of 23,380 launches that month and more than 75% of that year's launches.
What it does
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai - GitHub - kayba-ai/agentic-context-engine: 🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
Does a similar job
all alternatives →
TrailsJan 2026 · trails-red.vercel.app · ▲81Hey all, Justin here. I previously built Phind, the AI search engine for developers. One of the biggest problems we had there was figuring out what went wrong with bad searches. We had tons of searches per day, but less than 1% of users gave any explicit feedback. So we were either manually digging through searches or making general system improvements and hoping they helped. This problem gets harder with agents. Traces are longer and more complex. It takes more effort to review them, so I'm building a tool that lets you analyze LLM outputs directly to help developers of LLM apps and agents…
20+ Claude Code agents coordinating on real work (open source)Feb 2026 · github.com · ▲53Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
CodeRLM – Tree-sitter-backed code indexing for LLM agentsFeb 2026 · github.com · ▲81I've been building a tool that changes how LLM coding agents explore codebases, and I wanted to share it along with some early observations. Typically claude code globs directories, greps for patterns, and reads files with minimal guidance. It works in kind of the same way you'd learn to navigate a city by walking every street. You'll eventually build a mental map, but claude never does - at least not any that persists across different contexts. The Recursive Language Models paper from Zhang, Kraska, and Khattab at MIT CSAIL introduced a cleaner framing. Instead of cramming everything into…
An application stack Claude coded directly in LLVM IRMar 2026 · github.com · ▲10This repo is the result of a debate about what kind of programming language might be appropriate if humans are no longer the primary authors. Initially the thought was "LLMs can just generate binaries directly" (this was before a more famous person had the same idea). But that on reflection seems like a bad approach because languages exist to capture program semantics that are elided by translation to machine code. The next step was to wonder if an existing "machine readable" program representation can be the target for LLM code generation. It turns out yes. This project is the result of…
LLM, a Rust Crate/CLI for CPU Inference of LLMs (LLaMA, GPT-NeoX, etc.)2023 · github.com · ▲45G'day, HN! I'm one of the maintainers of `llm`. I've been working alongside a trusty group of contributors to bring this project to life, and we're now at a point where we're ready to share it with the world. Large language models (LLMs) are taking the computing world by storm due to their emergent abilities that allow them to perform a wide variety of tasks, including translation, summarization, code generation, and even some degree of reasoning. However, the ecosystem around LLMs is still in its infancy, and it can be difficult to get started with these models. `llm` is a one-stop shop for…
Phoenix OSS – Applying LLM Spans, Traces, and Evals for AI Insights2023 · github.com · ▲23We are the developers of Phoenix, which we released in April of this year with a goal of bringing LLM observability to the notebook. In the time since, the growth of LLM frameworks and complex agent workflows led us to add support for LLM spans and traces and introduce a simple Eval harness for testing the data from those spans. The latest Traces & Spans release of Phoenix offers: -Out of the box tracing for LlamaIndex and LangChain -Fully local execution, no data sent anywhere, outside of your own LLM calls -Ability to get a common dataframe format across frameworks back to a notebook for…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
