60 stories tagged with #harness, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Harness"
The Harness Has a Token Budget
Our project CLAUDE.md crossed 4,000 tokens last quarter, and the agent started missing rules it had...…
Show HN: Aura, an LLM coding harness that dogfooded itself
An AI coding harness that dogfooded itself into shape: Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. - CarpseDeam/Aura-IDE…
A harness for every task: dynamic workflows in Claude Code
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and s…
Harness Base Definition: The Control System Outside the Model
Previously, we split Agent into several minimal parts:…
System Boundaries: The Difference Between ChatBot, Workflow, Agent, and Harness
When people first build Agent systems, they often naturally read them as an upgrade path:…
Show HN: LiteHarness – One SDK for Claude Agent, OpenAI Agent, Pi AI
Unified Server for running OpenCode, Claude Code, Codex agents - LiteLLM-Labs/lite-harness…
Harness Acquires Codecov from Sentry
Harness acquires Codecov from Sentry to bring code coverage intelligence into software delivery governance for AI-accelerated engineering teams. | Harness Press…
Stop Shipping AI Slop: Build an Anti-Slop Harness Around Your LLM
"AI slop" is not a model problem. It's an engineering problem you decided not to solve. The slop is...…
Harness Engineering Course
Agent Harness Explained: Build Production-Ready AI Agents with Microsoft Agent Framework
Learn what an agent harness is, why it matters for production AI systems, and how to implement one step-by-step using Microsoft Agent Framework's create_harness_agent — with real P…
Scaling Laws for Agent Harnesses via Effective Feedback Compute
Agent harnesses increasingly determine the performance of language-model systems by deciding how models call tools, receive feedback, verify intermediate states, store memory, and …
Show HN: theta-spec - a humble harness agnostic configuration spec
harness agnostic configuration standard . Contribute to tamarillo-ai/theta-spec development by creating an account on GitHub.…
Stop Upgrading the Model. Start Engineering the Harness.
When a team hits a ceiling with their coding agent, the first instinct is to reach for a better...…
The Agent Harness Taught Me Why I Used to Fail
On building AI agents and accidentally understanding yourself Introduction We tend to...…
OpenAI Agents SDK: Building with Model-Native Harnesses - StartupHub.ai
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Show HN: What 1k Harness Experiments Taught Me About Self-Improving Agents
Project Repository: https://github.com/workofart/harness-experiment So I recently wanted to see whether an AI agent could self-improve a harness to solve terminal bench tasks. To a…
Show HN: VAEN – Package and import portable AI coding-agent Harnesses
Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config…
Show HN: Open-Source AI Racing Harness
Cadence v8.4: a multi-model coding harness where Claude writes, Codex reviews, and Bugbot triages
Claude writes. Codex reviews. Bugbot triages. Gemini sits on the council. ...…
Show HN: CoreTex – An Open-Source, Unix-like, biomimetic, flat-file AI Harness
A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. - mrdanielcasper/CoreTex…
AI has slashed coding time in 2026, but it’s sacrificed software stability
AI accelerates coding, but slows innovation at scale…
Impeccable: Design skills for AI harnesses
1 skill, 23 commands, and curated anti-patterns for impeccable frontend design. Works with Cursor, Claude Code, Gemini CLI, and Codex CLI.…
The AI Agent Harness: The Glue That Turns LLMs into Digital Workers
AI models have plateaued on raw intelligence. The next gains come from what you build around them.…
Designing a Modular Wiring Harness for Multi-Function Vehicle Trackers
How to allocate a 9-pin connector across 6 swappable modules for fleet, cold chain, security, and e-vehicle tracking.…
Harness Engineering: The New DevOps Layer for AI Agents
It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers
A prevalent assumption in LLM agent deployment holds that more structured harnesses universally improve reliability, and that higher-capability models need proportionally less st…
SIA: Self Improving AI with Harness & Weight Updates
Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The long-horizon goal of an AI th…
humble attempt at building a manifest centered configuration surface for arbitrary harnesses
theta: a humble approach to harness agnostic configuration
canonical implementation of the theta-spec. Contribute to tamarillo-ai/theta development by creating an account on GitHub.…
Token-level eval harness for tool-calling agents: what we wired up
TL;DR: We replaced our "did the agent finish the task" pass/fail eval with a token-level harness that...…
Polar: Agentic RL on Any Harness at Scale
Reinforcement learning for language agents increasingly depends on custom harnesses that manage long-running context, multi-turn tool use and multi-agent orchestration. However, po…
Building the harness around our coding agents: eight failure modes, eight pillars
Building the harness around our coding agents. Eight failure modes and pillars
Notes on the harness we built around Claude Code and Codex, organized as eight coding agent failure modes and eight harness pillars.…
Stord raises $250M to harness AI for e-commerce logistics
Harness, Scaffold, and the AI Agent Terms Worth Getting Right
We’re on a journey to advance and democratize artificial intelligence through open source and open science.…
Ask HN: Is Codex serving worse models or is it just the harness getting worse?
Harness Engineering: Stop Re-Prompting Your Coding Agent Every Session
Every time I started a new agent session, I was re-explaining the same things. The architecture...…
Stop Comparing LLM Agents Without Disclosing the Harness
This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely the infrastructure layer th…
DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations
Agent harness evolution improves frozen language-model agents by modifying the executable structures around them. We study this paradigm as a form of sample-efficient fast adaptati…
AION: Next-Generation Tasks and Practical Harness for Time Series
Time series research is moving beyond fixed forecasting benchmarks toward realistic tasks that combine prediction, contextual reasoning, tool use, and structured decision support. …
Moved from Harness to Revolte for delivery automation, what's the difference?
French Spider-Man rests mid-cliff at 60, no harness needed
Watch legendary rock and urban climber Alain Robert (often called "The French Spider-Man") casually stop to rest his arms in the middle of a climb at age 60 while in……
I made AI Agent Harness in node.js
New material could help NASA melt moon rocks, harness lunar resources
Your LLM Is Not an Agent. Your Framework Is Not Enough. You Need a Harness.
Introduction Every team building with AI agents hits the same wall. The demo works...…
Need Help Choosing a Harness for Qwen 3.6 27B
Stop Engineering Prompts: How an Eval-First Harness Let Us Ship 25 Algorithm Versions Autonomously
tl;dr — Agents are good at small fixes and terrible at "make this algorithm better" because every...…
TIL cancer can get cancer and it's called a hypertumor. hypertumors could theortically get harnessed and used to kill cancer sometime in the future as it steals the initial tumor's nutrients and starves it
Continual Harness: A reset-free self-improving harness for embodied agents
A reset-free self-improving harness for embodied agents. Pokémon Red, Emerald, and the Gemini Plays Pokémon experiments.…
Deepsec: The security harness for finding vulnerabilities in your codebase
Today we're open sourcing deepsec, an AI security harness that runs on your infrastructure, with your keys, against your code.…
What's Google Antigravity 2.0 ? Here's What the Agent Harness Actually Changes for Developers.
Google spent years telling developers that the IDE was the right place to put AI assistance. At I/O...…
The best cat harnesses
We tested 7 cat harnesses recommended by veterinarians and feline behaviorists to find the best options for walks and travel.…
Sensors and Guides: Two Ways Your Harness Talks to Your Agent
Birgitta Böckeler, writing about harness engineering at Thoughtworks, draws a distinction that turns...…
Harnessing medtech market alliances, ŌURA sets IPO plans in motion
New Material Could Help NASA Melt Moon Rocks, Harness Lunar Resources
Experts at Glenn Research Center in Cleveland recently discovered and tested a new material that could help NASA harness resources during future Moon missions.…
Anyone evaluated the difference between Qwen Code for the local qwen models vs another harness? CC, OC, LC, Aider etc..
Alibaba's proprietary Qwen3.7-Max can run for 35 hours autonomously and supports external harnesses like Anthropic's Claude Code
Agent Loop and Harness: A Practical Engineering View of AI Operations
A practical engineering guide to agent loops, harnesses, tool use, guardrails, observability, and security controls for production AI agents.…