coding-agents

BOUND is a deterministic control harness for AI agents. It sits between agent execution and the next decision, using observable evidence to choose ACCEPT, RETRY, REPLAN, or ROLLBACK.

GRID is a small framework for working with coding agents in a spec-driven way. The repository explains its purpose, basic workflow, and how it can be used in CI/CD to check for spec-code-test mismatches.

A r/place-style site for coding agents where artworks are generated, previewed locally, and merged into a homepage slot one at a time.

A small Bash wrapper that trims Maven output for coding agents while preserving exit status, failure diagnostics, and access to full logs.

A showcase of 27 explorable Three.js worlds built autonomously by 9 coding models from the same brief.

Lody is a local-first collaborative workspace for teams and coding agents. It brings conversations, runtime state, and code changes into one shared context layer, with open-source CLI and desktop client components.

A GitHub release for Microsoft’s Agent Lightning Skill, which helps coding agents optimize other AI agents using benchmarks and iterative improvements across prompts, tools, workflows, models, and reasoning settings.

A monthly poll that asks developers which AI coding agents they use and publishes the results.

Relaymux is a tmux-backed harness for running local coding agents, with Telegram as the remote control interface and support for iMessage/SMS in beta.

SecretSpec 0.12 adds audit logs and reason-required secret access for coding agents, with CLI, SDK, and config support.

A post about TMA1 v2, a local observability and context-sharing tool for coding agents. It adds an MCP server, hook-based context injection, and cross-agent sharing between Claude Code and Codex.

A multiplayer visual desktop for coding agents. It lets users copy agent instructions, open a shared desktop, and coordinate work and context alongside their coding agent.

An interactive, sourced deep-dive showing how Stack Overflow’s Q&A format helped train coding-focused AI systems and what happened as AI reduced public question volume.

Browser-based infrastructure for running coding agents persistently, with workspace management, status tracking, and support for tools like Claude Code and Codex.

A research preprint describing ADHD, a parallel divergent ideation method for LLM coding agents that isolates branches, uses cognitive frames, and then prunes with a separate critic pass.

A detailed technical article showing why git worktrees are a weak isolation boundary for parallel coding agents, with reproducible examples and practical implications for agent workflows.

A GitHub repository for a Minecraft skill that gives coding agents build-design abilities, JavaScript build recipe generation, vanilla .nbt export, and interactive previews before placing structures in-game.

Docker blog post about a real AI coding agent failure and how Docker Sandboxes aim to contain destructive execution mistakes.

A blog post describing an evaluation harness for comparing agentic coding tools and prompts across realistic SWE tasks, with token-cost results and model-specific behavior notes.

A Superconductor blog post showing how background coding agents were used to reproduce, diagnose, and fix a Rails memory leak using derailed_benchmarks, with a reusable Agent Skill workflow included.

A detailed article about the internal harness Nimbalyst built around Claude Code and Codex, covering context, provenance, capability, workflow, restraint, verification, visual interface, and coordination.