Cognits — Context-Oriented Generation for Neural Intelligent Tutoring Systems. Multi-agent AI personal tutor.
Project description
Cognits
Context-Oriented Generation for Neural Intelligent Tutoring Systems.
Multi-agent AI personal tutor: a Socratic orchestrator coordinates subagents (documentalist with local RAG, web researcher) to guide your learning from a local web interface, anchored to the project folder you're learning about.
Installation
uv tool install cognits
The installation includes the local RAG engine (onnxruntime + ChromaDB, ~600 MB). On first launch, the BGE-M3 embeddings model is downloaded (~2.3 GB).
Usage
cd my-learning-project
cognits
Starts a local server (port 5173 by default, PORT env var) and opens the
interface in your browser. State lives in ./.cognits/ (sessions, reports,
encrypted configuration, RAG index).
Development
scripts/dev.sh # Vite (HMR) + uvicorn --reload
scripts/build.sh # frontend build + wheel
uv run pytest
The frontend is a SolidJS SPA in frontend/; the backend is Python (FastAPI)
in src/cognits/.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file cognits-0.0.1.tar.gz.
File metadata
- Download URL: cognits-0.0.1.tar.gz
- Upload date:
- Size: 71.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5e954c387dabd5d0585f23ac39804f5a481268b251fa08e8806deba8fb1ef3ab
|
|
| MD5 |
a2e08a548adb78f1ae6ec5409ce5e06e
|
|
| BLAKE2b-256 |
31d1236f57747c5c9124831fcc7e7f659c10b87dc42a263bb75a68e448bd04df
|
File details
Details for the file cognits-0.0.1-py3-none-any.whl.
File metadata
- Download URL: cognits-0.0.1-py3-none-any.whl
- Upload date:
- Size: 48.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fd642ebb7e3a9e9e20a406da40f029f2aecbc5e600bec74511ea47b2fde2b67b
|
|
| MD5 |
8e4ba018ead63b0fd8edc68eb4c36a42
|
|
| BLAKE2b-256 |
cd7af4613cbb103a0bdfd5204518e958838bbd74674213ee2e7fcf475ac194b9
|
