2.7K RESULTS · “agents”
— · MIT
Prismer Cloud
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
— · MPL-2.0
One place to manage & connect to all your MCP servers
v0.1.29 · MIT
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Free.
v0.2.5 · no license
Native Claude Code, Codex and Pi adaptations of IdeaScientist for automatic, evidence-grounded research ideation.
Browser automation clicks buttons. OpenTabs calls APIs.
— · Apache-2.0
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
v4.1.11 · MIT
MCP server that gives AI assistants eyes and hands in the Godot editor: scene editing, input injection, deterministic game-time control, and live runtime state for agent-driven playtesting
Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.
Utilities for Android emulators, iOS simulators and real devices: launch, stream, control, record and automate them from a desktop app, TUI and CLI
v0.3.0 · Apache-2.0
Your First LLM-Wiki Conversation Knowledge Base
Dashboard for monitoring claude code sessions.
Agent Skill for Baidu Netdisk (百度网盘) — upload, download, transfer, share, search files via natural language. Works with Claude Code, Cursor, Codex, Gemini CLI, OpenClaw.
v1.2.1 · MIT
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
AI agent 通用任务治理框架:对齐目标与事实,规划和调度能力,守住授权与风险边界,治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.
Universal content reader MCP Server for 10+ platforms
v0.0.0 · Apache-2.0
Noodle CLI by Noodle Seed — author, run, and deploy declarative MCP servers. Embedding the assistant in your own web app is @noodleseed/assistant.
v1.0.206 · MIT
Rotate thousands of browsers behind one API, personas, proxies, stealth, CAPTCHA and MFA.
Don't reverse engineer it twice. 17,000+ open-source tools built by reverse engineering closed apps, APIs, devices, protocols, file formats, games and AI tools. Search site + agent skill + MCP server, refreshed nightly.
v1.0.1 · no license
Agent skill for repository-aware social preview images, visual directions, and GitHub-ready exports.
v4.4.0 · MIT
AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).
v0.4.2 · Apache-2.0
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
v0.2.0 · no license
Frontier model solution tracing, then made the prompting skills so Sonnet, GPT, DeepSeek, GLM, Kimi, ETC models work like that