Theo dõi tốc độ tăng trưởng và hoạt động, không chỉ tổng số stars.
Lend your AI wIthout giving away your keys.
OneMemory - one self-hosted SQLite memory store shared across your AI agents over MCP and a plain REST API, reachable from desktop, web, and your phone.
AI workers that turn GitHub issues into verified bug-fix pull requests: reproduce, fix with a regression test, prove it, open the PR. Runs locally with Claude Code, Codex, OpenAI, Gemini or Ollama.
The HDTP gateway: a self-hosted node that gives your AI agent an address other people's agents can reach (MCP over mTLS, sealed envelopes)
ContextBridge AI is a free Chrome and Microsoft Edge extension that helps you continue conversations across different AI assistants when you reach usage limits, run out of available messages, or simply want to switch platforms.
💔 Analyze a project to find out when it turned into AI slop
Can AI draw San Francisco from memory? Six LLMs, scored against OpenStreetMap. Code, every answer and the answer keys.
Eyes and ears for AI agents
OpenFlow — a visual builder for multi-agent AI workflows, built on the opencode engine
Self-hosted AI spend attribution for Anthropic, Claude.ai, OpenAI, Codex, OpenRouter, Cursor, and GitHub Copilot.
Yana AI 🐰 One runtime. Any AI. Human-governed. A local-first, cross-platform system for running, connecting, orchestrating, and governing AI — with deterministic control over what it can access, change, and execute. Your AI can act. But who decides how far it can go?
AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code, Cursor, and Codex.
Ask your CSV data questions in plain English and get an answer plus a chart. No pivot tables, no remembering which formula does what.
RTK pipeline · rtk pipeline add github:aeppling/rtk-pipeline-laya-delegate
A privacy-first, local AI background daemon that autonomously intercepts and patches Python crashes using Ollama and regex.
Simulate communities of AI agents around a “what if…?” question. Native, local-first macOS app (SwiftUI) that runs on the Claude, ChatGPT/Codex or Ollama you already use. Free and open source.
A minimalistic AI coding agent in 62 lines of bash, curl and jq. Step-by-step tutorial: LLM call → chat loop → tool-calling harness that writes and runs a Tetris game.
320 original sound effects for videos, animations and interfaces, with the data AI tools need to choose, place and mix each one. CC0.
Unofficial, source-available Android app for Multica, where people and AI coding agents share issues. Inbox with on-device notifications (no Firebase), Kanban board, task management, agent chat. Works with your own self-hosted Multica server. Early release v1.0.0. Not affiliated with or endorsed by Multica / Index Labs.
Educational guide for Non-Stochastic AI (NSAI).
Proof that AI work really happened: re-runs your checks in a clean copy the agent can't edit, and writes a receipt.
Skin is a verified, owner-controlled profile layer for the AI agent era so language models answer questions about people or companies with facts they published, not whatever they scraped.