coding agents
34 stories and discussions about coding agents, aggregated from every source we track.
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the…
I recently released JustHTML, a python-based HTML5 parser. It passes 100% of the html5lib test suite, has zero dependencies, and includes a CSS selector...
Why LLMs fail in production, why "more RLHF" cannot fix it, and how transferring 3 AM pager-duty trauma gives autonomous coding agents real survival instincts.
I wanted to run coding agents somewhere other than my laptop. Bivack gives each user a per-user AWS Lambda MicroVM with a persistent home on Amazon S3 Files, reachable from a browser terminal or a VS Code workbench. Here is how it works and what I learned building it.
Turn local AI models into a private, verified team of coding agents. - gmarland/local-coder
The only harness you need for coding. Relay keeps what every run learns, re-tests every task, and runs on your machine with your model.
Viaduct is a C4 modeling tool for software teams, with a hosted MCP server that feeds your architecture to AI development tools. System context, container, component and code diagrams, live collaboration, and change…
I spent a weekend playing with Jev, a model that scores things instead of writing text. It became a code search tool that makes Codex, OpenCode and Claude Code faster, measured over 162 sessions.
Bloom is a free native Mac app that runs Claude Code and Codex in parallel, each in its own git worktree. Read the diffs, comment inline, open the pull request.
System-level friction telemetry for coding agents — capture papercuts from any harness, close them with real fixes - nibzard/papercut
Clean up what your apps and coding agents left running. A free, open-source macOS menu-bar app. - arpwal/leftovers
What an agent harness is, and why the same model solved 43 tasks in one harness and 72 in another. With Claude Code, Codex and six more coding agents compared.
High-performance MCP server for AI coding agents: persistent knowledge graph, blast radius analysis, semantic search. Built in Rust. - spuentesp/lain
Groundtrack turns agent work into reusable engineering judgment, evidence-backed initiatives, and measurable organizational improvement.
During my last holiday I spent a good chunk of its 2 weeks working on a new side project (more about it in a future post!). A lot has changed with coding agents recently, and it has been a while since I’ve had to push…
An easy-to-use, secure macOS sandbox for Claude and other AI coding agents - minoansecurity/sidekernel
Jev can classify turns cheaply, but it cannot tell a router how hard a task is. The signal we needed was in the agent's trajectory, not the prompt.
AI coding agents that prove their work. Gates, a tamper-evident record, and a PR check that blocks anything unproven.
DeepSWE audit finds AI coding agents optimize for imagined graders, not users—a hidden reward hacking pattern.
Contribute to CTNicholas/multiplayer-coding-agents development by creating an account on GitHub.
See what keeps going wrong, get a debrief of how you drove each session, and carry approved lessons into future Claude Code and Codex sessions.
When my most experienced engineer got tired of our shitty code
A programmable control plane where every coding harness and your local dev stack can work together.
Last time, we covered AI risks inside and against your organization, and how to reduce them. In this post, we’ll touch on some specific risks and mitigations for using coding agents. Coding agents are a specific case…
Using Open-Weight Models in Local Coding Harnesses as an Alternative to Claude Code and Codex Subscriptions
Paste a public GitHub repo. Meet its lockfile personality. Bring receipts.
Coding Agent Sandboxes. Contribute to discobox-ai/discobox development by creating an account on GitHub.
Vigil keeps your Mac awake while your coding agents work, and lets it sleep again when they stop.
Working memory for AI coding agents, yours and your team's. Sessions from Claude Code, Codex and Cursor become one living graph of decisions, files and the ties between them, queryable by your ...