{"data":{"slug":"itayinbarr-little-coder","name":"little-coder","tagline":"A harness optimized for smaller LLMs","github_url":"https://github.com/itayinbarr/little-coder","owner":"itayinbarr","repo":"little-coder","owner_avatar_url":"https://avatars.githubusercontent.com/u/12065558?v=4","primary_language":"TypeScript","stars":2606,"forks":179,"topics":["ai-coding-assistant","aider-polygot","benchmark","code-generation","coding-agent","coding-agents","local-llm","ollama","qwen","small-language-models","terminal-bench","tool-use"],"archived":false,"github_pushed_at":"2026-09-18T22:17:59+00:00","maintenance_label":"Very active","stars_delta_30d":238,"url":"https://www.graphcanon.com/tools/itayinbarr-little-coder","markdown_url":"https://www.graphcanon.com/tools/itayinbarr-little-coder.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/itayinbarr-little-coder","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=itayinbarr-little-coder","description":"A harness optimized to smaller LLMs","homepage_url":"https://itayinbarr.github.io/little-coder/","license":"Apache-2.0","open_issues":3,"watchers":13,"ai_summary":"Offers an environment and tools for optimizing the performance of small language models.","readme_excerpt":"## Install\n\nOne-line install (Node.js 22.19+ required):\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/itayinbarr/little-coder/main/install.sh | bash\n```\n\nOr with npm directly:\n\n```bash\nnpm install -g little-coder\n```\n\nOr with [bun](https://bun.sh):\n\n```bash\nbun add -g little-coder\n```\n\nThat's the whole install. No clone, no `npm install` in a workspace, no PATH fiddling. `little-coder` is now on your PATH and works from any directory.\n\n> **Note for `bun add -g` users.** The launcher (`bin/little-coder.mjs`) is a Node.js script with `#!/usr/bin/env node` at the top, so Node ≥ 22.19 still has to be on your PATH for the binary to start — bun is fine for installing/updating the package, but the runtime is Node. If you want a fully node-less setup, replace the shebang in `$(bun pm bin -g)/little-coder` with `#!/usr/bin/env bun`.\n\n---\n\n# Add 'make' (with word-boundary) and 'docker compose ps' on top of the defaults\nexport LITTLE_CODER_BASH_ALLOW=\"make ,docker compose ps\"\n\n---\n\n# Follow that version's README for its Python setup (pip install -e .)\n```\n\nThe paper ran `ollama/qwen3.5` through the Python little-coder at commit **`1d62bde`** (tag [`v0.0.2`](https://github.com/itayinbarr/little-coder/releases/tag/v0.0.2)). The 45.56 % mean figure is the average of two full 225-exercise runs on that exact codebase. For the 78.67 % headline, check out tag [`v0.0.5`](https://github.com/itayinbarr/little-coder/releases/tag/v0.0.5) — both are pre-pi Python and follow the pre-pi setup.\n\n---\n\n---\n\n## License\n\nApache 2.0 — see [LICENSE](LICENSE) for details. NOTICE tracks upstream attribution.","github_created_at":"2026-04-11T10:37:11+00:00","created_at":"2026-07-15T10:58:28.114983+00:00","updated_at":"2026-09-20T04:59:57.973318+00:00","categories":[{"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"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai-coding-assistant","name":"ai-coding-assistant"},{"slug":"code-generation","name":"code-generation"},{"slug":"coding-agents","name":"coding-agents"},{"slug":"small-language-models","name":"small-language-models"}],"trust":{"provenance":{"is_fork":false,"github_id":1207740274,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T04:59:55.662Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":17,"days_since_push":1,"last_release_at":"2026-09-18T22:16:38Z","stars_delta_30d":238,"open_issues_delta_30d":-16},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:58:29.378Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T04:59:56.684Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T04:59:56.684Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-20T04:59:56.684Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T04:59:56.684Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T04:59:56.684Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["If you are developing AI applications using smaller LLMs that need to maintain good performance metrics but lack the infrastructure to support larger models.","To efficiently train and optimize code generation and coding agents with local LLMs, as it supports environments like TypeScript which can be crucial for specific development needs."],"when_not_to_use":["Avoid little-coder if your project necessitates the extensive computational abilities provided by large language models to handle complex tasks beyond the scope of small LLM capacities.","Not suitable when targeting a broad range of models; its specialization in smaller models might limit flexibility compared to more general frameworks that support both big and small models."],"source":"enrich:decision_facts","observed_at":"2026-07-17T10:15:09.399Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"little-coder focuses on providing an optimized environment for small language models, enabling better performance without requiring extensive computational resources."}]}}