Developer Tool AI Tools

A local Rust-plus-Python middleware layer for LLM apps that claims to reduce token usage and add in-process security checks before prompts are sent to a provider.

A macOS command-line tool for on-device AI and voice tasks, including speak, listen, transcribe, chat, and an OpenAI-compatible local server.

An open NDJSON specification for AI crawler ingestion and site content graphs, with examples and reference files in the repository.

INFINI is an open-source portable agent loop spec and reference implementation for defining workflows in a Loopfile and running them across engines. The repo includes a CLI, mock-mode execution, trace comparison, audit checks, and a prototype UI.

Cachet is a local semantic cache for LLM APIs that sits in front of OpenAI- or Anthropic-compatible endpoints and serves repeated or rephrased requests from cache. It includes a dashboard for hit rate and estimated savings, supports streaming responses, and is implemented as a single Rust binary.

A tiny GPT implementation in pure Go, trained on Jules Verne books, with runnable code and notes that explain the model’s evolution and design choices.

A loopback HTTPS proxy that swaps placeholders for real API keys at request time, keeping secrets out of the agent process. It uses Bitwarden Secrets Manager and supports scoped bindings for hosts, methods, and paths.

AutoGPU is an open-source project for using AI agents to design and harden a GPU-like chip end to end, from Verilog through synthesis and place-and-route to GDSII. The repo shows a concrete fp8 matmul accelerator flow, quick-start steps, and documentation for running the design/hardening process.

An open-source shim that lets Cursor canvas .tsx files render on the web by aliasing cursor/canvas to a Mantine-backed implementation. Includes install steps, runtime setup, supported API coverage, limitations, and a live example deployment.

Open-source local compute fabric for AI agents. It runs a single-node K3s stack through Docker Compose, provisions isolated Ubuntu sandboxes, and exposes native MCP support for local agent workflows.

An experimental RAG lab for constrained environments, with configurable document classification, chunking, retrieval, reranking, and chat context assembly. It includes Open WebUI integration and emphasizes debugging retrieval and context failures.

Kit is a developer workspace that combines an editor, Chromium browser, terminal, email, calendar, whiteboard, and autonomous agent with shared AI context across the whole environment.

Stage CLI is an AI-powered code review tool that groups local changes into logical chapters and helps users review what matters before diving into the code. It works with any AI agent, installs via npm, and can be invoked as a local command to open a browser-based review UI.

A governed memory runtime for AI assistants with typed storage, policy checks, audit logging, tenant isolation, and hybrid retrieval. The repo includes a backend API, worker jobs, SDK examples, architecture docs, and eval harnesses.

A service-boundary-aware coordination layer for heterogeneous LLM code agents via MCP. It combines versioned Markdown documents, pub-sub notifications, diff-aware updates, and a web dashboard for browsing, search, and AI chat.

A GitHub repository that packages Claude Desktop for Linux with install paths for Debian/Ubuntu, Fedora/RHEL, Arch AUR, and NixOS, plus MCP support and system integration features.

A Mac-resident MCP server that lets AI agents access Apple services like Mail, Calendar, iCloud Drive, Voice Memos, Reminders, and Contacts over a Tailscale network with per-token ACLs and audit logging.

A Pi extension that uses AI to generate and keep codebase documentation current, with commands for initial docs, incremental updates, and chat-based questions.

Local-first browser tool for reviewing rendered markdown like a Google Doc, with AI agents (Claude or Codex) turning comments into inline answers or real git diffs.

Open-source shared memory for AI coding agents that records decisions, rejected alternatives, and contradictions across sessions.

Agentize is a Claude Code-oriented framework for assessing and improving how ready a codebase is for AI agents. It includes two maturity models, runnable assessment and improvement commands, and installable skills for project or personal use.

UltraCompress is a Python-based compression tool for large language models. The repo describes lossless 5-bit transformer compression, verification via SHA-256, a CLI on PyPI, and published model packs on Hugging Face.

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.

A local AI coding harness that turns business-rule specs into a constrained JSON AST, validates it, and compiles it into Clojure code while logging generation and repair artifacts.