developer tools

A llama.cpp fork that adds a JEV-compatible decision API for Choice, Score, and Noul evaluations while keeping standard LLM inference support.

Open-source, self-hosted platform for running managed AI agents like Claude Code, Codex, Hermes, DeepSeek Harness, and Pi on infrastructure you control.

OpenAPPA is an open-source deterministic guardrail and information-flow policy engine for LLM agents. The page describes flow-based security labeling, CI validation, remedy plans, sanitizers, authorities, and subagents, with links to docs, GitHub, Discord, and benchmark claims.

A Vercel article showing how to use GPT-6 Sol with the AI SDK evaluation API to assess draft replies, score evidence-based answers, and read structured results in TypeScript.

AI code security scanner that reviews a repository, flags exploitable issues, and provides a scoped fix prompt for each finding.

A LangGraph-based workflow that generates, benchmarks, validates, and iterates CUDA kernels using a C++/CUDA harness. It targets workload-specific optimization with support for NVIDIA research lookup and optional Nsight Compute profiling.

A local gateway for Claude Code that logs tool calls, enforces approval rules, and trims noisy tool output to save tokens.

A Mac notch app that surfaces Claude Code and Codex approval prompts in the menu bar/notch so developers can approve or deny requests without switching back to the terminal.

An unlisted pastebin for HTML or Markdown files that’s built for coding agents and quick sharing. It supports one-command publishing, agent-driven workflows, and renders Markdown into readable pages.

Open-source control plane and proxy for managing multiple MCP servers behind one endpoint, with routing, policy, auth, logging, and rate limiting.

A framework for dbt development that uses AI agents with structured specs, deterministic infrastructure controls, and numeric diffs instead of code-only review.

A benchmark writeup comparing GraphQL-over-MCP and REST-over-MCP setups, showing lower token use and inference cost for GraphQL in agentic tasks.

A macOS voice assistant for Claude Code that talks through project ideas, writes specs, launches builds, and alerts you when a session needs attention.

AirmailAI is a BYOK LLM chat app with a browser-extension backend that lets users connect their own keys and chat with providers like OpenAI, Anthropic, Google, and OpenRouter. The page highlights privacy-by-design messaging, file upload, web search, and zero-markup pay-as-you-go usage.

A terminal CLI that watches a Git repository and streams edits as they happen, making it easier to monitor what coding agents or editors are changing in real time.

A detailed post from pact0 about testing whether blank AI agents could complete a real product workflow, what failed, and the fixes they shipped after the audit.

ObserverBench is an interactive benchmark and guided demo for testing whether internal AI monitoring methods help make safer decisions, not just better predictions. It includes real-model results, benchmark tasks, and a no-login walkthrough showing how warning scores affect review and harm that slips through.

OpenAI’s documentation for its Agents API, covering how to build and run cloud agents with the OpenAI platform. The page surfaces core concepts, quickstart material, SDKs, webhooks, tracing, tools, and related agent-building resources.

Open-source text-to-SQL engine tuned to your own database, with configurable pipeline stages, policy checks, and an evaluation harness for measuring performance on real schemas.

brw is a semantic browser control tool for agents. It runs a real visible Chrome/Chromium browser and exposes control through MCP and HTTP, with stable refs, semantic page snapshots, and post-action observations.

An open-source Stripe-like payment layer for AI agents and paid MCP tools, with spend authorization, per-call charging, and settlement flows for test credits in beta.

A self-hostable MCP endpoint that centralizes accounts, memory, skills, secrets, and access controls for AI agents. It supports multiple providers, profile-based permissions, audit logs, and deployment on your own machine or cloud.

Hedgemony is a Python tool that checks AI-written code for fabricated packages, invented APIs, impossible calls, and contradictions between code and stated examples, using interpreter and registry checks rather than another model.

Open-source benchmark that measures which developer tools LLMs recommend when asked to build real web apps. It runs fixed prompts against a panel of models, parses the tool recommendations, and publishes rankings and head-to-head comparisons.