Top Picks

Experimental page-aware Metal runtime and reproducibility harness for running oversized sparse mixture-of-experts models on Apple Silicon. The repo documents GPT-OSS 120B support, performance results on 64 GiB and 16 GiB machines, and the runtime/harness structure.

A Markdown-based personal finance CLI built with Claude that uses AI for receipt and expense transcription while keeping totals and settlements deterministic in code.

Open-source, self-hostable platform for shipping Claude Code-style AI agents to Kubernetes or local Docker Compose, with Slack as the first supported channel. The README shows a command-line workflow, deployment tiers, and support for traces, evals, budgets, and model choices.

Bullet is a fast coding agent for macOS that focuses on lower-latency routing, targeted code search, and parallel tool execution. The page highlights a private beta, free access, and an internal demo with SWE-bench Verified results.

A Hacker News reader focused on searching stories and comments, filtering noise, and browsing discussions with recency and text-based matching controls.

crosswalk is an MCP-based social context-sharing product for coding agents, letting teams share searchable posts and pull group knowledge into tools like Claude Code, Cursor, Codex, and VS Code.

Open-source team skills for bringing shared coding standards, directives, and evals into agentic coding workflows like Claude Code and Codex.

A small Rust-based LLM proxy for forwarding chat, messages, and responses requests to providers with gateway-key handling and optional protocol translation between Anthropic and OpenAI styles.

A free checker that measures whether ChatGPT, Gemini, Claude, and Perplexity recommend your brand, with prompt-level gaps, cited sources, and competitor comparisons.

A lightweight CLI for running multiple local MLX models on Apple silicon. It serves OpenAI-compatible endpoints, supports both text-only and multimodal models, and can browse/download from Hugging Face.

Bifrost is a high-performance AI gateway that provides a single OpenAI-compatible API across 23+ model providers, with automatic failover, load balancing, semantic caching, and enterprise deployment features.

A browser extension that masks personal and sensitive information before you send messages to AI chat tools, then restores the original values in the reply.

A suite of three native macOS apps: Crest for notch-based control, Take for screen recording, and Minutes for on-device meeting notes. The page emphasizes offline use, local processing, one-time pricing, and how the apps work together on a MacBook notch.

A Windows tray widget that shows Claude Code and Codex rate-limit usage, reset times, and burn pace. It runs locally, uses the user’s own Claude OAuth token and Codex CLI data, and includes install and build instructions.

A local-first longevity research workspace that combines a bilingual knowledge library, AI-assisted note capture, and evidence-oriented search across public biomedical sources.

A GitHub repository that turns untrusted source material into compact AI skills using evidence gates, validation steps, and audit output.

Open-source Python library that lets developers integrate an LLM into the Python runtime so missing attributes, methods, and typed values can be inferred on demand with confidence scores.

A type-safe Go runtime for building tool-using LLM agents across multiple providers, with streaming, memory, and OpenTelemetry support.

An open-source web font system that renders protected text normally for readers while serving a decoy version to scrapers that read raw HTML.

Memsprout is a shared AI-context layer for teams. Its docs show an MCP server, team spaces, role-based access, and a quickstart for connecting agents and sharing memories across teammates' clients.

A local MCP server that lets AI apps like Claude Desktop and Codex search, read, create, update, open, trash, and restore macOS sticky notes with permission-based access.

A Rust-based coding agent built for speed, low memory use, and Claude Code compatibility. The project highlights support for skills, hooks, MCP, plugins, sub-agents, and multiple LLM providers, with terminal, headless, and IDE-facing entry points.

A single-binary software catalog for platform engineering with auto-discovery, dependency graphs, scorecards, and a native MCP server for AI coding agents.

Banksia is an open-source Python project for building and running accountable AI teams. The repo shows a CLI install flow, a local console, workflow studio, run monitoring, and support for reusable teams and durable state.