The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.
The spend meter, cost/margin, & budget gate for AI voice agents. Meters STT + TTS + LLM + telephony per call, out of the box (Pipecat, LiveKit — Python & TypeScript). Hard-stops the next turn before it crosses your ceiling. Local, no account, no telemetry. Built by Floe.
This Agent MCP allows you to train external intelligence with zero GPU and let you trade it at Tetrees EX
Local-first CLI for agent skills, browser automation, knowledge bases, external CLIs, and terminal AI chat.
Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.
RSIH — versionable, shareable agent harness: Pi coding agent + Genome config layer
AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发执行，让变更有依据、交付有证据。用创意编织现实。
Open-source CLI, schemas, resolver, and DSH agent tools for DSH Plugin Hub
Browser teleoperation data for embodied AI — elizaOS-ready episodes, trajectory_db converter, onchain provenance. The fuel station for agent robot stacks.
Build LangGraph agents like Next.js apps.
Harnessclaw is a powerful, Electron-based desktop application designed to manage, chat with, and operate AI agents and skills seamlessly.
Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.
Multi-agent demo platform for Titans (arXiv:2501.00663) — neural networks that learn to memorize at test time. 7 AI agents, native desktop UI.
An AI agent for writing API documentation. Supports a vibe-coding approach to authoring API docs, with a built-in friendly doc viewer and API mocking tools.
Open-source app builder engine — intent to working app
fskill-creator turns your long-text SKILL into functions, making it modular, testable and trackable for better long-term maintenance and iteration
For You Agent - a personal, portable digital persona for the AI era. Carries your models, AI accounts, skills, prompts and workflows into every AI tool.
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.
ApeAdmin is a Python backend management framework for modern AI applications, built on FastAPI and Vue3, 100% open source, with built-in RBAC permission control and audit logging as enterprise-grade basics. It integrates an MCP-SSE gateway with a rich plugin ecosystem, helping developers quickly build applications with both business management and AI tool output capabilities.
🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.
Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya
Free, open-source curriculum for making money with generative AI image, video, and audio — for creators and agencies.
Launch and manage anti-detect browsers with unique real-device fingerprints for multi-account operations, web scraping, ad verification, and AI agent automation.
Local-first creator favorites workbench with evidence-preserving Markdown capture and a complete browser UI.