HCP-Coder
Hierarchical Context Pruning for code completion using pre-trained large language models
GraphCanon updated 2w · GitHub synced 2w
Decision brief
Hierarchical Context Pruning (HCP) for optimizing real-world code completion tasks with repository-level pre-trained models
Good fit when
- When deploying a solution that requires precise and context-aware code completions within the bounds of project repositories, leveraging HCP-Coder can enhance efficiency
- Suitable if you have a large codebase where traditional methods of code completion do not adequately handle hierarchical or contextual nuances
Avoid when
- Avoid using for smaller projects that do not require extensive context pruning since the setup and overhead might outweigh benefits
- Not ideal when working with languages that lack comprehensive pre-trained models, as HCP-Coder's performance hinges on repository-level pre-training
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (625d since push)
- As of 2w
- Provenance
- Not a fork · Personal account
- As of 2w
- Security (OSV)
- 49 low (49 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install HCP-CoderSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
HCP-Coder provides an approach to optimize real-world code completion tasks with repository-level pre-trained models.
Capability facts
- Languages
- python
Source: github.language · Aug 5, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 5, 2026)
- Run `pip install -r requirements.txt` to install all requirements.Source link
Tags
README
Requirements
- Run
pip install -r requirements.txtto install all requirements.
For agents
This page has a .md twin and JSON over the API.