Developer Tools AI Tools

An Apple Silicon–optimized inference build of Bonsai 1.7B with custom Metal kernels, benchmark results, quick-start instructions, and a bundled OpenAI-compatible server.

Open-source AI agent harness tool that lets an agent wipe its session context and replay the first message, designed for loop-based agent workflows.

A Visual Studio 2026 extension that connects Claude Code to the IDE, showing native diffs with accept/reject, selection context, compiler diagnostics, and a live session panel.

A routing skill that helps coding agents choose the most token-efficient tool for a task instead of reading whole files or dumping verbose output into context. It recommends tools like serena, graphify, rtk, caveman, or plain Read/Grep/Bash depending on the job.

An agent skill and Python builder that turns Markdown note folders from Obsidian or gbrain into an interactive HTML knowledge map with a force graph, growth timeline, filters, and note detail panels. The repo includes a prebuilt demo for quick inspection and supports use in Claude Code, OpenAI Codex, Cursor, and simila

Python library that automates ChatGPT and Gemini through the web UI, using a real Chrome browser to send prompts, upload files, and return responses as Python objects.

A local-first desktop environment for dispatching coding tasks to any model and any agent, with diff review, terminal streaming, task history, and per-project configuration.

Dropstone is a versioned coding agent runtime that routes work through open-weight models on US-hosted, no-retention infrastructure. The report explains its monthly re-baselining process, safety boundary, and cost model for Fast, Pro, and Heavy tiers.

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.

Visr is a CLI tool that records full agent terminal trajectories, including commands, output, retries, and fixes, then returns a transcript link for reuse across sessions.

Teleport-Env is an ultra-fast OS-level snapshot and rollback sandbox for autonomous coding agents, built with overlayfs and CRIU. It targets destructive agent testing, MCTS search loops, and reinforcement learning workflows that need rapid environment recovery.

A tool that analyzes local Claude Code logs to show where tokens, time, and cost go across a month of usage, including re-reading context, cache reads/writes, and subagent activity.

AWS DevOps blog post explaining how to build a self-extending CLI using Amazon Bedrock, the Strands Agents SDK, and MCP. It outlines the workflow, technical pieces, and repository availability for readers who want to replicate the pattern.

An open-source bridge that lets AI IDE chat sessions resume asynchronously from timers, shell commands, or webhooks. It supports VS Code GitHub Copilot Chat and Windsurf, with local HTTP endpoints and a quick-start flow shown in the repo README.

A GitHub repository that proposes a practical methodology for evaluating how AI systems behave during real work, with quick-start, practitioner, and methodology guides included.

TokenScale is a browser-based AI API pricing explorer that compares 16 providers, converts token costs into familiar real-world examples, and shows how batch, cache, and conversation length affect spend.

An open-source ID library that generates human-readable, token-efficient IDs for AI agents and LLM workflows, with parsing, validation, deterministic IDs, and alias mapping utilities.

An experimental autonomous bare-metal OS agent that uses an LLM, VirtualBox, and screenshot inspection to iterate on low-level code, boot a VM, and refine behavior from execution results.

A TypeScript markdown parser built for incremental streaming, aimed at parsing LLM markdown output on the server or client. It exposes a typed AST, supports CommonMark and GFM tables, and includes examples for full and streaming parsing.

GitHub Blog article on reducing token usage and API cost in agentic coding workflows, including logging token usage, removing unused MCP tools, replacing GitHub MCP with GitHub CLI, and measuring efficiency gains.

Tokenyst is a local-first CLI for tracking Claude Code token usage and API costs against task budgets. It captures session spend, shows progress in the terminal, and stores data on your machine.

An open-source browser experiment that uses a visual LLM to read HTML and hallucinate the rendered page instead of using a traditional rendering engine.

Google Developers Blog post about integrating DFlash, a diffusion-style speculative decoding framework, into the vLLM TPU ecosystem to improve LLM serving speed on TPU v5p.

An essay arguing that the BEAM runtime and OTP primitives map well to agent workloads, especially long-lived personal-assistant agents with supervision, registries, and structured concurrency.