{"id":30020427,"url":"https://github.com/yonasvalentin/codecontext-ai","last_synced_at":"2026-05-16T08:34:57.618Z","repository":{"id":307345358,"uuid":"1029221441","full_name":"YonasValentin/codecontext-ai","owner":"YonasValentin","description":"🔒 Privacy-first AI models for code documentation. Your code stays on YOUR machine. Forever.","archived":false,"fork":false,"pushed_at":"2025-07-30T17:55:02.000Z","size":66,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-30T20:35:10.512Z","etag":null,"topics":["ai","documentation","local-ai","machine-learning","ollama","open-source","privacy","privacy-first"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/YonasValentin.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-07-30T17:48:03.000Z","updated_at":"2025-07-30T17:55:05.000Z","dependencies_parsed_at":"2025-07-30T20:35:12.754Z","dependency_job_id":"d8bd6db3-374d-4ff1-bdc6-32aa8fa150fe","html_url":"https://github.com/YonasValentin/codecontext-ai","commit_stats":null,"previous_names":["yonasvalentin/codecontext-ai"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/YonasValentin/codecontext-ai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YonasValentin%2Fcodecontext-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YonasValentin%2Fcodecontext-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YonasValentin%2Fcodecontext-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YonasValentin%2Fcodecontext-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YonasValentin","download_url":"https://codeload.github.com/YonasValentin/codecontext-ai/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YonasValentin%2Fcodecontext-ai/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269005891,"owners_count":24343408,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-06T02:00:09.910Z","response_time":99,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","documentation","local-ai","machine-learning","ollama","open-source","privacy","privacy-first"],"created_at":"2025-08-06T02:01:56.699Z","updated_at":"2026-05-16T08:34:57.576Z","avatar_url":"https://github.com/YonasValentin.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CodeContext AI™\n\nPrivacy-first AI models for automated code documentation generation. Train and run specialized documentation models locally without external dependencies.\n\n## Features\n\n- **Local Processing**: All inference runs locally with no external API calls\n- **Specialized Models**: Fine-tuned models for README, API documentation, and changelog generation\n- **Privacy Focused**: No data transmission or telemetry collection\n- **Production Ready**: Docker support, comprehensive testing, and CI/CD integration\n\n## Installation\n\n### Quick Setup (Recommended)\n```bash\n# Automated setup with virtual environment\nchmod +x setup_environment.sh\n./setup_environment.sh\nsource venv/bin/activate\n```\n\n### Manual Setup\n```bash\n# Create virtual environment\npython3 -m venv venv\nsource venv/bin/activate\n\n# Install dependencies\npip install torch transformers pyyaml\npip install -r requirements.txt\npip install -e .\n```\n\n## Quick Start\n\n```bash\n# Run advisory analysis demo\npython demo_advisory.py\n\n# Train advisory model\nmake train MODEL=advisory\n\n# Analyze code with advisory system\npython -m codecontext_ai.guidance_cli analyze myfile.py --type refactor\n\n# Scan directory for issues\npython -m codecontext_ai.guidance_cli scan ./src --type security\n```\n\n## Architecture\n\n### Models\n\n| Model | Purpose | Base | Training |\n|-------|---------|------|----------|\n| codecontext-readme-7b | Project documentation | CodeLlama-7B | QLoRA fine-tuning |\n| codecontext-api-7b | API documentation | CodeLlama-7B | QLoRA fine-tuning |\n| codecontext-changelog-7b | Release notes | CodeLlama-7B | QLoRA fine-tuning |\n\n### Training Pipeline\n\n- **Base Model**: CodeLlama-7B with 4-bit quantization\n- **Fine-tuning**: Parameter Efficient Fine-Tuning (PEFT) with LoRA\n- **Optimization**: GGUF format for efficient local inference\n- **Evaluation**: Multi-metric assessment (BLEU, ROUGE-L, semantic similarity)\n\n## Development\n\n### Setup\n\n```bash\n# Development environment\nmake install-dev\n\n# Prepare training data\nmake prepare-data\n\n# Run tests\nmake test\n\n# Type checking and linting\nmake lint \u0026\u0026 make typecheck\n```\n\n### Training\n\n```bash\n# Train specific model\nmake train MODEL=readme\n\n# Train all models\nmake train-all\n\n# Convert to GGUF format\nmake convert-gguf MODEL=models/codecontext-readme-7b\n```\n\n### Evaluation\n\n```bash\n# Evaluate model performance\nmake evaluate MODEL=models/codecontext-readme-7b.gguf\n\n# Run comprehensive benchmarks\nmake benchmark\n```\n\n## Configuration\n\nTraining configurations are stored in `configs/`:\n- `readme.yaml`: README model parameters\n- `api.yaml`: API documentation model parameters\n- `changelog.yaml`: Changelog model parameters\n\n## Privacy\n\n- No external API calls during training or inference\n- All processing occurs locally\n- Open source codebase for transparency\n- No data collection or telemetry\n\n## Performance\n\nBenchmark results on RTX 4090:\n- Inference speed: 30-40 tokens/second\n- Memory usage: 4-8GB RAM\n- Model size: ~4GB per specialized model\n\n## Contributing\n\n1. Fork the repository\n2. Create feature branch\n3. Add tests for new functionality\n4. Run test suite: `make test`\n5. Submit pull request\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for detailed guidelines.\n\n## License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n## Support\n\n- Issues: [GitHub Issues](https://github.com/YonasValentin/codecontext-ai/issues)\n- Discussions: [GitHub Discussions](https://github.com/YonasValentin/codecontext-ai/discussions)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyonasvalentin%2Fcodecontext-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyonasvalentin%2Fcodecontext-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyonasvalentin%2Fcodecontext-ai/lists"}