Developer Tools AI Tools

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.

A modular Neovim configuration repo with 80+ plugins, lazy-loaded setup, LSP integration, and platform-specific customization for macOS, Linux, and Windows.

Pu.sh is a lightweight coding-agent harness delivered as a shell script. The page shows a direct install-and-run flow, a no-dependency setup, and links to GitHub, docs, and an MIT license.

A French public demo of an autonomous Claude agent competing in timed money-making challenges, with live episode tracking, Stripe payments, and public results from prior runs.

Pulse is an AI incident response tool that watches systems, diagnoses PagerDuty incidents with Claude, and posts suggested fixes to Slack for one-click resolve or escalation.

CodeZero is a no-code backend and automation platform that now includes AI flow generation, a module system, and an execution results view inside the IDE.

Humbug is an open-source, GUI-based agentic development platform for human-AI collaboration. The page says it supports multi-model workflows, local and cloud LLMs, tool use, approvals for risky actions, and local-first data handling.

A side-pane companion for Claude Code that shows daily AI news and spaced-repetition concepts while the agent is working, then hides when it needs user attention.

Hawkeye is a developer tool for fast local code search and navigation across large codebases, with editing, focused replace, tabs, shortcuts, and Perforce support.

A live demo that shows an AI agent using KINETK’s API/MCP workflow to analyze live social signals and generate an evidence-backed launch and growth plan for a product prompt.

Open-source email firewall that classifies inbound mail into SILENT, QUEUE, PUSH, or AUTO using a deterministic policy around LLM-scored signals.

Attestor is a TypeScript control plane for high-risk AI-driven operations. It sits between an AI-generated request and the real system action, applying policy, approval, scope, freshness, replay, and evidence checks before returning admit, narrow, review, or block.

A curated learning roadmap for building production AI agents, covering OpenAI, Anthropic, MCP, harnesses, evals, memory, and safety. The README organizes the material into phases with exercises and a prioritized reading table.

A custom Claude Code status line script that shows workspace, model, session, context usage, token totals, code churn, and 5-hour/7-day rate-limit runway in two colored rows.

A macOS utility that keeps a MacBook awake while AI agents are running, then lets normal sleep resume when they go idle. It includes install scripts, hooks for Claude Code and Codex, and a menu bar status indicator.