A registry of agent benchmarks (including many OSS agent trajectories)

Scored 65.2% vs google's official 47.8%, and the existing top closed source model Junie CLI's 64.3%. Since there are a lot of reports of deliberate cheating on TerminalBench 2.0 lately (https://debugml.github.io/cheating-agents/), I would like to also clarify a few things 1. Absolutely no {agents/skills}.md files were inserted at any point. No cheating mechanisms whatsoever 2. The cli agent was run in leaderboard compliant way (no modification of resources or timeouts) 3. The full terminal bench run was done using the fully open source version of the agent, no…

Hi! I’m Nathan: an ML Engineer at Mozilla.ai: I built agent-of-empires (aoe): a CLI application to help you manage all of your running Claude Code/Opencode sessions and know when they are waiting for you. - Written in rust and relies on tmux for security and reliability - Monitors state of cli sessions to tell you when an agent is running vs idle vs waiting for your input - Manage sessions by naming them, grouping them, configuring profiles for various settings I'm passionate about getting self-hosted open-weight LLMs to be valid options to compete with proprietary closed models. One…

Single-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…

Hi HN, we're Kiran and Vijay! Over the past two years, we have built a columnar storage engine for observability: logs, metrics, and traces. Today, it's exciting for us to show what we've built on top of that foundation: LLM Agent Observability. Given how non-deterministic agents are, storing all traces without sampling was critical for us. But these traces tend to be in the MBs, sometimes GBs - we needed to store them inexpensively. We also needed the queries and analyses to be fast. To meet both these goals, we store them in S3 in our own parquet-like file format, and query them using AWS…

We recently started to use agents to update some documentation across our codebase on a weekly basis, and everything quickly turned into cron jobs, logs, and terminal output. it worked, but was hard to tell what agents were doing, why something failed, or whether a workflow was actually progressing. We thought it would be more interesting to treat agents as long-lived workers with state and responsibilities and explicit handoffs. Something you can actually see and reason about, instead of just tailing logs. So we built Clawe, a small coordination layer on top of OpenClaw that lets agent…

I'm Josh, founder of Synth. We've been working on coding agent optimization with method like GEPA and MIPRO (the latter of which, I helped to originally develop), agent evaluation via methods like RLMs, and large scale deployment for training and inference. We've also worked on patterns for memory, processing live context, and managing agent actions, combining it all in a single stack called Horizons. With the release of OpenAI's Frontier and the consumer excitement around OpenClaw, we think the timing is right to release a v0. It integrates with our sdk for evaluation and optimization but…