SOTA long memory eval with open source models
Cursor published a great post last week on scaling long-running autonomous coding agents to build a browser. We’ve been exploring a similar idea, but applied to math proofs We show how a swarm of agents, coordinated via shared memory, can generate a Lean proof for a non-trivial multi-step math problem-Putnan A2-that a single agent struggled with. We were feeling fancy so we wrote a full post and captured the runtime. Harness will be public soon(tm) for you to run it yourself.
SOTA long memory eval with open source models launched on March 3, 2026 with 5 votes, #1,928 of 23,380 launches that month and more than 75% of that year's launches.
What it does
Automated research for world models. Ensue plugs into your repo, builds the evaluation framework with your team, and runs constant experiments on dedicated GPUs. Verified breakthroughs ship as production-ready PRs, and Ensue is only paid when your benchmark moves.
Ensue plugs into your repo, builds the evaluation framework with your team, and runs constant experiments on dedicated GPUs. Verified breakthroughs ship as production-ready PRs, and Ensue is only paid when your benchmarkfrom ensue.dev
Does a similar job
all alternatives →
Chunk sidecarsMay 2026 · circleci.com · ▲77Hi HN! My name is Olaf, I work at CircleCI as a technology advisor in the CTO office, came in through the acquisition of my company Vamp.io (progressive delivery for microservices on k8s) in 2021. Wanted to hear the HN community feedback and thoughts on a project we think could be very interesting when adding AI coding agents to the SDLC and your CI pipelines. Our team at CircleCI built Chunk sidecars after repeatedly running into the same issue internally: by the time our CI catches a failure, the agent has already moved on and most of the useful context is gone. The basic idea of Chunk…
- IBI built a toy TPU that can do inference and training on the XOR problem2025 · tinytpu.com · ▲134
We wanted to do something very challenging to prove to ourselves that we can do anything we put our mind to. The reasoning for why we chose to build a toy TPU specifically is fairly simple: - Building a chip for ML workloads seemed cool - There was no well-documented open source repo for an ML accelerator that performed both inference and training None of us have real professional experience in hardware design, which, in a way, made the TPU even more appealing since we weren't able to estimate exactly how difficult it would be. As we worked on the initial stages of this project, we…
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…
Oodle.ai – $10 per million agent tracesJul 2026 · oodle.ai · ▲31Hi 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…
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 · 29d 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
