A developer built an error notebook for an AI coding agent, accumulating 266 rules over two months that intercepted 66 instances of the same error pattern. The system uses action-type rules triggered …
SmallDocs, a new command-line tool that creates lightweight, private documents for coding agents, launched to integrate with AI assistants like Claude, Codex, and Cursor. The tool renders Markdown fil…
Atlarix, an agent workstation for open-weight models, resolved 42 out of 89 tasks on Terminal-Bench 2.0 compared to opencode's 39 out of 89, using the same model and identical infrastructure. The 3-ta…
A developer benchmarked five local LLM agents on an RTX 3090, finding that the orchestrator, not the model, determines success. GLM-4.5-Air scored 0% with opencode but 93% with a LangGraph agent, whil…
Poly Grid, a tiling multi-terminal grid for macOS, launches to let developers run AI coding agents like Claude Code and Codex in parallel, with features for broadcasting prompts and piping panes. The …
Videowright, a new open-source tool, lets users create animated explainer videos from a single prompt by generating video segments, AI voiceovers, and syncing audio within coding agents like Claude Co…
A developer describes shifting from Claude to local LLMs like Qwen 3.6 35A-3b to preserve engineering struggle and discipline, arguing that frontier models remove both friction and struggle while loca…
Taste, a zero-configuration tool for AI agents, compresses context from 56K to 1.9K tokens by automatically learning coding patterns from git history and session logs, enabling agents to write project…
AI DevKit launches a local control plane for AI coding agents, enabling shared configuration, memory, and cross-agent communication across tools like Claude Code, Codex, and Cursor. The tool addresses…
A developer automated database backups across a fleet of servers using the remote-agents MCP server, which connects each host to an encrypted relay room. The setup includes a Postgres primary, two str…
A developer built opsx, a workflow tool that enforces a spec-first approach to AI-assisted coding, requiring a reviewed change document before any code is written. The tool separates management and go…
A test of local AI models for coding tasks found that consumer hardware cannot run models capable of autonomous software development. Devstral 24B and Qwen3.5 122B-a10b failed to complete a simple fil…
Developer Geoff McCaughan released Sidekick, a self-hosted AI agent platform with persistent memory and 70 MCP tools that can extend itself without code changes. The platform runs on a remote machine,…
Legioni, a team of AI coding agents that coordinates work and learns from every task, has been released as an open-source tool. The agents plan, implement, review, and test code, with lessons from eac…
Termem, a cross-agent memory and session management tool for the terminal, indexes sessions from coding agents like Claude Code, Codex, Gemini, opencode, and shell by directory, enabling recall, resum…
ContextSpy, a context window profiler for large language models and AI coding agents, launched to help developers visualize and reduce token usage. The tool intercepts LLM API requests to analyze prom…
A developer built a coding agent that responds to Telegram messages and drives a tmux pane on a local machine. The setup uses OpenClaw as a Telegram gateway, pinned Node.js and pnpm versions, and a re…
A developer introduces OpenClaw, a gateway that maps Telegram supergroup topics to individual coding agents running on a remote machine. The design allows users to dispatch and supervise agents from a…
A developer reduced the reflect phase of the `akm improve` pipeline from 35 minutes to 8 minutes by eliminating unnecessary overhead. The new LLM mode makes direct HTTP calls to the LLM endpoint inste…
AI coding agents operate as a simple control loop: they build a message bundle, send it to an LLM, execute any requested tool calls, and repeat until the task is done. The LLM never directly executes …