{"data":{"slug":"reid41-qa-pilot","name":"QA-Pilot","tagline":"Interactive chat project for GitHub code repository navigation","github_url":"https://github.com/reid41/QA-Pilot","owner":"reid41","repo":"QA-Pilot","owner_avatar_url":"https://avatars.githubusercontent.com/u/25558653?v=4","primary_language":"Svelte","stars":326,"forks":41,"topics":["deepseek","glm","huggingface","langchain","localai","nvidia","openai","svelte","tongyi","zhipuai"],"archived":false,"github_pushed_at":"2025-08-24T03:40:52+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/reid41-qa-pilot","markdown_url":"https://www.graphcanon.com/tools/reid41-qa-pilot.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/reid41-qa-pilot","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=reid41-qa-pilot","description":"QA-Pilot is an interactive chat project that leverages online/local LLM for rapid understanding and navigation of GitHub code repository.","homepage_url":null,"license":"Apache-2.0","open_issues":8,"watchers":8,"ai_summary":"QA-Pilot uses LLMs to provide interactive understanding and navigation of GitHub repositories through Svelte frontend.","readme_excerpt":"# docker run -p 8080:8080 --gpus all --name local-ai -ti localai/localai:latest-aio-gpu-nvidia-cuda-11\n\n---\n\n# docker run -p 8080:8080 --gpus all --name local-ai -ti localai/localai:latest-aio-gpu-nvidia-cuda-12\n\n---\n\n# install deps\ncd svelte-app\nnpm install\n\nnpm run dev\n```\n\n8. Run the backend QA-Pilot in another terminal:\n\n```shell\npython qa_pilot_run.py\n```","github_created_at":"2024-04-03T03:11:52+00:00","created_at":"2026-07-11T10:40:14.327492+00:00","updated_at":"2026-08-07T18:01:57.629614+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"deepseek","name":"deepseek"},{"slug":"glm","name":"glm"},{"slug":"huggingface","name":"huggingface"},{"slug":"langchain","name":"langchain"},{"slug":"localai","name":"localai"},{"slug":"nvidia","name":"nvidia"},{"slug":"openai","name":"openai"},{"slug":"svelte","name":"svelte"}],"trust":{"provenance":{"is_fork":false,"github_id":781254183,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-07T18:01:56.899Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":348,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":181,"high_count":0,"last_scan_at":"2026-07-11T10:40:15.818Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-07T18:01:57.328Z"},"languages":{"value":["svelte"],"source":"github.language","observed_at":"2026-08-07T18:01:57.328Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-07T18:01:57.328Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free under the Apache-2.0 license, but users might incur costs related to GPU usage for performance."},"requirements":{"notes":["Requires Docker for setup.","Benefits from access to NVIDIA GPUs via Docker configurations for enhanced performance."],"min_ram_gb":null,"requires_docker":true},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":true},"when_to_use":["Use QA-Pilot if you need to leverage both local and online large language models (LLMs) for quick insights into GitHub code repositories.","Consider QA-Pilot when your workflow requires GPU support, as it can accommodate NVIDIA GPUs through Docker configurations."],"when_not_to_use":["Avoid using QA-Pilot if you do not have access to Docker or local GPU resources necessary for running the tool effectively.","QA-Pilot might not be suitable if your repository is large and complex, leading to potential performance issues with real-time LLM responses."],"source":"enrich:decision_facts","observed_at":"2026-07-15T09:46:53.238Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":true},"decision_summary":[{"label":"Pricing","value":"freemium - Free under the Apache-2.0 license, but users might incur costs related to GPU usage for performance."},{"label":"Requirements","value":"Requires Docker; Requires Docker for setup.; Benefits from access to NVIDIA GPUs via Docker configurations for enhanced performance."},{"label":"Adopt for","value":"QA-Pilot is an interactive chat tool for navigating and understanding GitHub repositories using LLMs, built with Svelte."},{"label":"License detail","value":"The Apache-2.0 license allows use in both open-source and commercial contexts while requiring attribution."}]}}