Minimum context. Maximum understanding.
Project description
TerseContext
Minimum Context. Maximum Understanding. For you and for an LLM.
TerseContext is a code indexing system that produces the smallest, highest-confidence context window for LLMs working with codebases. It combines static analysis (AST/graph) with dynamic analysis (runtime traces) to give LLMs exactly what they need — and nothing they don't.
Status
Pre-alpha. Active development.
How it works
- Parses your codebase into a knowledge graph using Tree-sitter
- Enriches nodes with observed runtime behavior from your test suite
- Merges static and dynamic signals with provenance tags
- Serializes the minimum sufficient subgraph for any given query
Coming soon
- Python parser (Tree-sitter)
- Neo4j graph writer
- Qdrant vector writer
- Runtime trace instrumentation
- Query pipeline
- Serializer
License
MIT
Release history Release notifications | RSS feed
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 tersecontext-0.1.0.tar.gz.
File metadata
- Download URL: tersecontext-0.1.0.tar.gz
- Upload date:
- Size: 4.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4b4c4f30a73b26eb3b109e8a1a4c4fb7c5dd4a4eb77f8873effa70f0e7fe6a44
|
|
| MD5 |
c564458108fd9ea24b90e83c8638a716
|
|
| BLAKE2b-256 |
3ff9d26f228a74a382d0b26637874f842d26cca1fd3411a489f3d3456da7e98e
|
File details
Details for the file tersecontext-0.1.0-py3-none-any.whl.
File metadata
- Download URL: tersecontext-0.1.0-py3-none-any.whl
- Upload date:
- Size: 2.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cb9c8aaf6b07fb38a9ccc2a5c67f7a78aca20effc1d888ba88867f7bc3d7d2ab
|
|
| MD5 |
b302dc574848cb0a99ae4323b373e7f8
|
|
| BLAKE2b-256 |
d16f586ce675b1877c031a9f77642ac6759ecd73971eb208ab87d840d5336817
|
