we just released a new blog "Training a coding... agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:show more

We built the best codebase search to give any... agent grounded information from GitHub repos. Introducing Sandbox Search. Point it at any repo, and we’ll spin up a secure coding agent in its own sandbox to do research for you. Use inside claude code, openclaw, cursor, and more.show more

You can now do RL weight sync over HF... Buckets. > Async GRPO + LoRA in TRL > train on one Job, serve vLLM on others > sync just the small delta adapter through a Bucket. Trainer, inference and storage, all on Hugging Face infra. Beautifully optimised loop by @DirhoussssiAmine 👇 3h27 → 53 min for the same reward.show more

The craft of engineering is rapidly changing. At Ramp,... we built our own background coding agent to accelerate faster. We call it Inspect. It wrote 30% of merged frontend + backend PRs in the past week. It’s powered by OpenCode, Modal and Cloudflare Developers. It runs fully in the cloud, and starts in seconds, letting every builder work at the speed of thought, no setup required. Today, we’re open sourcing the full blueprint so anybody can build their own Inspect. Just give our spec to your current coding agent, and let it build your new favourite.show more

New open-source agent harness just landed! I got early... access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.show more

This is pure f*cking treasure. ex-Google engineer reveals his... AI agent playbook. 14+ years at Google. $0 to read it. the topic is harness engineering: everything around the model that lets it execute, check its work and recover when something breaks. one example in his breakdown deserves attention. LangChain’s coding agent went from 52.8% to 66.5% on Terminal-Bench 2.0. the model stayed the same. the team changed the prompts, tools and machinery around it. Agent = Model + Harness. the system has six practical jobs: > guides give the agent project rules, constraints and examples > sensors check its work through tests, linters and validators > the loop handles execution, verification, retries and escalation > memory preserves state, artifacts and decisions > permissions control which tools and actions are allowed > observability records tool calls, costs and failures the part worth stealing is what happens after a mistake. an agent keeps declaring broken code finished. you add a verification step before completion. it keeps ignoring a project convention. you add a targeted instruction and a check for that specific failure. it touches files outside its task. you tighten its write permissions. each recurring failure gives you a concrete improvement to make in the harness. that improvement can carry into every future run. this is where the engineering work compounds. bookmark it. start with the mistake you have already paid your agent to make twice.show more

You can now give your Agent its own: +... Profile + Wallet + DMs + Network One setup prompt. No human in the loop required. An open playground for people and agents to interact. Works with Hermes, Openclaw and any other harness. Copy the prompt below ↓↓↓show more

▣ Introducing Endless: infinite inference (kinda). An experimental harness... to milk every ounce out of your Codex subscription. Since Codex can let an in-progress turn keep going even after your usage hits 100%, why not put that to the test? Endless starts one Codex turn and gives the agent a wait_for_user_input tool. Once it finishes a task, it calls that tool and waits. Your next message becomes the tool result, keeping the entire session inside the same turn. It runs through Codex’s own app server using your existing ChatGPT login. Native tools, automatic compaction, context tracking, and quota tracking still work as usual. ⚠️ NOTE: I CAN’T CONFIRM THAT YOU WON’T GET BANNED OR PUNISHED FOR USING THIS TOOL. USE IT AT YOUR OWN RISK.show more

this is f*cking beyond comprehension. Google engineers just shipped... the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.show more

AGENT ARCHITECTURE ROUTES WORK. IT DOES NOT REMEMBER WORK.... THAT GAP IS WHY YOUR LOOP KEEPS FIXING THE SAME BUG TWICE. these are two different engineering problems. every agent that silently drifts is missing one of them. architecture answers what runs. harness → loop → graph. it defines the tools, the retries, the branching routes, the approval gates. context ops answer what the run knows. write → read → compress → isolate. it defines what gets saved between attempts, pulled in on read, summarized on overflow, and split across sub-agents. for two months i believed a solid harness plus a verifier loop was enough. my coding agent kept re-discovering the same test failure across retries. the loop was working. it just had nowhere to write what it had already learned. here is the decision rule: if your agent forgets across restarts, add write and read. if it stalls on long tasks, add compress. if two sub-agents step on each other, add isolate. architecture without context ops is a well-routed system with amnesia.show more

OpenCode says it has reached 13M monthly users, 4.6M... weekly users and roughly $40M in annualized revenue. Anthropic restricted competing coding tools. OpenCode works with any model, which gives teams a way around building their coding stack on one lab.show more

Don't train the model, evolve the harness. I read... a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.show more

EXCUSE ME?? IQuest raised a 320B model from its... very first token, then gave it over a million exams with three proctors on every single one the exams are real executable containers. one check runs while the environment gets prepped, one while the code executes, and a full trajectory audit after. if the model tries to peek at hidden tests, it gets flagged, so every pass it learns from is earned it's called IQuest-Q1, an open model built to live in your terminal → 15B active out of 320B, only 8 of 256 experts per token → 29T training tokens, context stretched 32K → 128K → 512K → SFT, RL in real environments, then multi-teacher distillation (MOPD) → runs inside Claude Code, Codex and other agent scaffolds my favorite speed trick: an MTP layer gets reused as a drafter that guesses the next tokens, and the main model checks them. long sessions get way cheaper on the same parameter budget the team calls this an early release. a first model with training this strict makes me want to see the second one try it:show more

After Andrej Karpathy released autoresearch, where an agent runs... experiments in a loop on its own, I packed his method into one prompt that turns Opus 5.5 into a graph and can carry almost any task to the finish. → writes a check that can actually fail, first → splits the task into parts → runs the independent parts in parallel → loops each one until it passes the check → sends back only the part that failed → turns every mistake into a rule for next time → calls you only for the step that can’t be undone Throw it at Opus 5.5 with the task you’ve been putting off for a week, and you’ll see the difference in one run. The full prompt is in the comments. How to tune it for your own work is in the article below. Save it before it gets lost ↓show more

Vorflux has opened its new cloud platform, allowing users... to run tasks from a plan to a merged PR on a dedicated machine. It can plan, build, test, and review on its own. > Diff reviews are done by a different model family than the one that wrote it by default. > First boot is saved as a snapshot, with all subsequent sessions waking up from that same starting point. > A browser agent walks through the real user flow, and the recording is included in the pull request. Video proof in the PR 👀show more

this is straight f*cking gold the full harness guide... for Kimi K3, the #1 open source frontend model the premise: the model underneath keeps changing. the harness is the part that stays yours what one night of it looks like: 02:00 - the trigger fires, every node that needs work gets picked > 212 agents fan out, one per node > a bad return gets rejected, retried once with the reason attached > one agent tries to write outside its folder. blocked. nobody woken up > +41 nodes and +96 edges land in the graph > a drafted email hits pre_send and waits for you 02:41 - the loop stops on its own, inside a 45 minute budget 07:30 - you read one file and make two decisions the whole machine is one folder, one config file, five short scripts two rules hold it together: > the model sits behind one line, so a better model is a config change > the verifier lives outside the agent, so nothing grades its own work now the money part companies burn whole quarters building internal agent platforms a harness setup for a small team goes for four figures, one time then a monthly retainer to run the swap test on every new model release models come and go. the person who owns the harness keeps getting paidshow more

this is literally f**king insane i just 2x my... usage limits on $200/mo codex i figured out how to use deepseek v4.1-flash on $10/mo opencode go for routine subagent work... while gpt-6 astra directs the project and sol handles implementation. here's how to set it up in 3 mins: → connect opencode go to codex through model-router → install quota flow, including its skill and agent profiles → open a fresh astra task and paste: quota flow tells flash to handle discovery and checks, sol to implement, and luna to review when needed. the same implementation agent keeps its context through the build → test → fix loop. every extra agent should earn its call.show more

300 AI AGENTS QUIETLY RUN 99% OF A REAL... COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.show more

Muse Spark open weights (even in NVFP4) is an... amazing computer use agent I shipped an e2e tutorial on building an env for a browser agent (with OpenEnv, Helium and Hugging Face Sandboxes) enjoy 🤗 here's a small visualized run ⤵️show more

Check out this real-world example of the freeway driving... scenario we broke down on our blog last week: On a beautiful morning on the Loop in Houston, TX, the Nuro Driver perceives a cut-in, predicts its evolution, and decides the safest response is to brake smoothly and create room. #NuroDriver #AutonomyForAll #AllRoadsAllRides #SelfDriving #AutonomousVehicles #AIshow more

sorry, they just did WHAT someone gave a machine... one disease name, the leading cause of blindness in the developed world with 1.5 million americans already in its path, and it came back pointing at a drug that has sat in pharmacies for years under a different label: 551 papers read in 30 minutes against the 294 hours a human would have needed, and the loop that did it is public on GitHub most agent setups answer one question at a time, so the ceiling on the work is the quality of the question you happened to think of this one was handed a single question and wrote the second one itself. turns out that follow-up is where the real find was: a target called ABCA1, upregulated threefold, in an experiment no human ordered i read the whole paper looking for the trick, and the trick is structural. that is the second question, and it is the gap between an assistant and a factory: - hand the loop a field rather than a task: it was given a disease, and choosing the mechanism was part of its job - make it rank before it spends: 151 papers in, ten candidate mechanisms out, scored against each other before anything touched a bench - split reading from judging, so the agent that forms the theory is a different agent from the one grading it - close every cycle on physical reality: the verdict was an experiment, and another model's opinion was never allowed to stand in for one - feed each result back as the next question rather than a log line, which is the step almost nobody builds - search what already passed inspection first: the winner was an approved compound with a safety file already on record - write down what the round learned before opening the next one, so round two starts where round one stopped my read, and i think it is the uncomfortable one: reading was the entire bottleneck in that field, and everybody spent the decade optimising the writing. people ran every physical experiment here, the analysis agent needs a domain expert writing its prompts, and the authors decline to call this the leap it resembles. the thinking got replaced, and the hands did not so the question i cannot answer for my own setup: which step of your loop still stops dead until you sit down and type something bookmark this one. the four parts that turn one model into a line that runs like this, the queue, the rooms, the write permissions and the gate, are built file by file in the piece below ↓show more