Cognithor
Cognithor - Agent OS: Local-first autonomous agent operating system. 16 LLM providers, 17 channels,
Rating
Votes
0
score
Downloads
0
total
Price
Free
API key required
Works With
About
Cognithor · Agent OS
A local-first, autonomous agent operating system for AI experimentation and personal automation.
Cognition + Thor — Intelligence with Power
18 LLM Providers · 18 Channels · 6-Tier Memory · Knowledge Vault · Security · Apache 2.0
Note: Cognithor is in active development (Beta). While the test suite is extensive (13,117 tests, 89% coverage), the project has not been battle-tested in production environments. Expect rough edges, breaking changes between versions, and some German-language strings in system prompts and error messages. Contributions, bug reports, and feedback are very welcome. See Status & Maturity for details. For non technical users, wait until version 1.0.0 for stable long term support.
[](https://clawdboard.ai/user/Alex8791-cyber)
Weekly Recap: Rank #1 | $1,644 spent vibe-engineering
Vibe-Engineered, not vibe-coded. Cognithor is not a weekend hack held together by AI-generated spaghetti. Every module follows a deliberate architecture (PGE-Trinity, 6-phase gateway init, 3-layer security), backed by 13,117 tests, structured plans, spec compliance reviews, and code quality gates. The AI writes the code — but a human engineers the system. There's a difference.
Why Cognithor?
Most AI assistants send your data to the cloud. Cognithor runs entirely on your machine — with Ollama or LM Studio, no API keys required. Cloud providers are optional, not mandatory.
It replaces a patchwork of tools with one integrated system: 18 channels, 125+ MCP tools, 6-tier memory, knowledge vault, voice, browser automation, Computer Use, and more — all wired together from day one. 13,117 tests at 89% coverage keep it honest. See Status & Maturity for what that does and does not guarantee.
In plain terms: Cognithor is an AI assistant that lives entirely on your computer. You talk to it through your terminal, a web UI, Telegram, Discord, or any of 18 supported channels — and it talks back, remembers what you said last week, and acts on your behalf. It can search the web, write and edit files, run shell commands, control your browser, automate your desktop (clicking, typing, reading windows), manage your calendar, and learn new skills over time. Think of it as a local, private, self-improving Jarvis.
Unlike cloud-based assistants, Cognithor keeps all your data on your machine. Your conversations, memories, documents, and credentials never leave your hardware unless you explicitly configure a cloud LLM provider. It works fully offline with Ollama or LM Studio, and it encrypts everything at rest with SQLCipher (AES-256). If privacy matters to you — and it should — this is the architecture you want.
Don't lose this
Three weeks from now, you'll want Cognithor again. Will you remember where to find it?
Save it to your library and the next time you need Cognithor, it’s one tap away — from any AI app you use. Group it into a bench with the rest of the team for that kind of task and you can pull the whole stack at once.
⚡ Pro tip for geeks: add a-gnt 🤵🏻♂️ as a custom connector in Claude or a custom GPT in ChatGPT — one click and your library is right there in the chat. Or, if you’re in an editor, install the a-gnt MCP server and say “use my [bench name]” in Claude Code, Cursor, VS Code, or Windsurf.
a-gnt's Take
Our honest review
This plugs directly into your AI and gives it new abilities it didn't have before. Cognithor - Agent OS: Local-first autonomous agent operating system. 16 LLM providers, 17 channels, . Once connected, just ask your AI to use it. It's completely free and works across most major AI apps. This one just landed in the catalog — worth trying while it's fresh.
Tips for getting started
Tap "Get" above, pick your AI app, and follow the steps. Most installs take under 30 seconds.
Heads up: this needs an API key to work. You'll get one from the service's website (usually free). The setup guide tells you exactly where.
What's New
Imported from GitHub
Ratings & Reviews
0.0
out of 5
0 ratings
No reviews yet. Be the first to share your experience.