Trending

Codeknow turns a codebase into a queryable knowledge graph for architecture analysis, impact detection, drift tracking, onboarding tours, and refactoring guidance. It runs without LLM keys, supports 25+ languages, and exposes a broad CLI plus export formats and interactive views.

A searchable index of AI Engineer talks with summaries, timestamps, packs, speakers, topics, and conference filters. It helps users jump to the relevant parts of long talks and browse related sessions by theme or speaker.

Self-hosted multiplayer AI workspace in Python for team-based agent collaboration, with governed actions, real-time shared rooms, and a tamper-evident audit log.

Keyboard-first desktop Kanban workspace for AI coding agents with embedded terminals, git worktrees, and hook-driven task tracking. It supports workflows for task search, project filtering, notifications, live AI session tracking, and keyboard-driven board control.

OpenCrew is an open-source multi-agent orchestration layer built on Claude Code. It lets users add agents, route work through a Captain orchestrator, review approvals before tools run, and keep full git-style version history for agent configs and runs.

Spewer is a local service for delegating bounded coding tasks to cheaper models, with durable task state and evidence-rich receipts. The repo shows install, ask, background task, watch, check, and cancel flows, plus local Ollama/Qwen3 support.

Grith is an OS-level security supervisor for AI coding agents on Linux. It intercepts syscalls, scores risky actions, pauses ambiguous ones for human review, and can deny dangerous calls before they run.

Open-source agent skill and Python service for stripping AI provenance marks from text and files. It supports multiple hosts, includes install scripts, hooks, and a service-backed workflow for cleaning watermarks across many file types.

Rust library for building modular, scalable LLM applications and agentic workflows. It supports multi-turn streaming, multiple model providers, vector store integrations, and agent runtime abstractions.

Open source platform for teams to deploy and manage coding agents in one shared workspace, with chat, bots, schedules, notifications, and access to a real computer.

OpenSpender gives AI agents a self-custodial wallet so they can pay for model and tool calls with per-request, daily, and total caps. It connects through MCP and supports clients like Claude Code, ChatGPT, Codex, and opencode, with itemized spend and a catalog of x402 and MPP services.

Agentize is an open-source tool that lets websites expose a first-party semantic search/index interface for AI agents. It builds a semantic index from owner-selected sources, serves Markdown and canonical URLs from the site’s own domain, and supports local embedding generation.

Self-hosted ebook library that runs on object storage. It can run as a Cloudflare Worker over R2 or as a Node server over a directory, with support for EPUB and PDF reading, search, downloads, profiles, and reading positions.

A Ruby gem that encodes the Vercel AI SDK Data Stream protocol for Rails and Rack backends, so Ruby apps can stream text, reasoning, tool calls, and data parts to useChat/useObject.

Open-source repository for a NanoGPT training speedrun, focused on getting a 124M model to target loss on 8x H100 GPUs in under 90 seconds. The README includes run commands, Docker instructions, and a detailed list of model and systems optimizations.

A portal layer that unifies multiple MCP servers behind one endpoint so AI clients can connect once and use three meta-tools instead of dozens or hundreds of exposed tools.

ImageSage is a private, local AI gallery for Windows that lets you search photos by visual content or text in images, then review AI-generated rename suggestions and manage files in place.

OzBrain is a hosted shared knowledge base for AI agents and teams. It lets tools like Claude, ChatGPT, and Cursor read and write the same source of truth, with connector setup, staged writes, conflict handling, and version history.

Meridian is a local-first work journal for developers that reconstructs screen activity into a daily timeline, summary, and draft worklog or standup updates, with ticket drafting for Jira-style workflows.

An open-source MCP server and bench CLI for agent-driven firmware development on physical hardware. It lets coding agents compile, flash, read serial output, debug boards, and manage OTA/fleet workflows for ESP32-class devices.

Open-source embodied AI agent that uses a camera, stylus, and dedicated phone to operate iPhone apps like a person would, without APIs, ADB, or software installed on the phone.

fx is a tiny open-source coding agent and CLI written in Zig. The page shows it as a minimal, model-agnostic tool built for research, embedding, and low-footprint local or cloud use, with WASM support and a shell-like interface.

A browser-based Sokoban game with a client-side AI solver that finds provably optimal fewest-move solutions for most boards and explains how the solver works.

A native macOS Postgres GUI that can draft SQL from natural-language questions, using either a configured cloud model or Apple’s on-device Foundation Model on supported Macs.