{"data":{"node":{"slug":"niansong1996-lever","name":"lever","tagline":"Supports learning to verify language-to-code generation with execution","github_url":"https://github.com/niansong1996/lever","owner":"niansong1996","repo":"lever","owner_avatar_url":"https://avatars.githubusercontent.com/u/10934810?v=4","primary_language":"Python","stars":90,"forks":8,"topics":[],"archived":false,"github_pushed_at":"2023-07-05T09:06:23+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/niansong1996-lever","markdown_url":"https://www.graphcanon.com/tools/niansong1996-lever.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/niansong1996-lever","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=niansong1996-lever"},"categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"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":"code-verification","name":"code verification"},{"slug":"execution-based-verification","name":"execution based verification"},{"slug":"language-to-code","name":"language-to-code"}],"edges":[],"neighbours":[{"slug":"alibaba-open-code-review","name":"open-code-review","tagline":"Hybrid architecture code review tool with LLM Agent for precise line-level comments and built-in security rule checks.","github_url":"https://github.com/alibaba/open-code-review","owner":"alibaba","repo":"open-code-review","owner_avatar_url":"https://avatars.githubusercontent.com/u/1961952?v=4","primary_language":"Go","stars":20812,"forks":1482,"topics":["agent","agent-skills","code-review","code-review-assistant","harness","repository-level-context"],"archived":false,"github_pushed_at":"2026-08-19T11:05:53+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/alibaba-open-code-review","markdown_url":"https://www.graphcanon.com/tools/alibaba-open-code-review.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alibaba-open-code-review","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alibaba-open-code-review","shared_categories":[]},{"slug":"tanweai-pua","name":"pua","tagline":"A skill package for enhancing the functionality of AI agents within development environments","github_url":"https://github.com/tanweai/pua","owner":"tanweai","repo":"pua","owner_avatar_url":"https://avatars.githubusercontent.com/u/256783335?v=4","primary_language":"TypeScript","stars":19454,"forks":1185,"topics":["agency","agent","pip","pua"],"archived":false,"github_pushed_at":"2026-07-16T05:58:58+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/tanweai-pua","markdown_url":"https://www.graphcanon.com/tools/tanweai-pua.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tanweai-pua","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tanweai-pua","shared_categories":[]},{"slug":"zai-org-codegeex","name":"CodeGeeX","tagline":"CodeGeeX is an open multilingual code generation model implemented in Mindspore and available via PyTorch.","github_url":"https://github.com/zai-org/CodeGeeX","owner":"zai-org","repo":"CodeGeeX","owner_avatar_url":"https://avatars.githubusercontent.com/u/223098841?v=4","primary_language":"Python","stars":8809,"forks":688,"topics":["code-generation","pretrained-models","tools"],"archived":false,"github_pushed_at":"2024-08-13T05:59:38+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/zai-org-codegeex","markdown_url":"https://www.graphcanon.com/tools/zai-org-codegeex.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zai-org-codegeex","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zai-org-codegeex","shared_categories":["model-training"]},{"slug":"swe-bench-swe-bench","name":"SWE-bench","tagline":"Benchmark for assessing language models' capability to resolve real-world Github issues","github_url":"https://github.com/SWE-bench/SWE-bench","owner":"SWE-bench","repo":"SWE-bench","owner_avatar_url":"https://avatars.githubusercontent.com/u/139597579?v=4","primary_language":"Python","stars":5576,"forks":930,"topics":["benchmark","language-model","software-engineering"],"archived":false,"github_pushed_at":"2026-07-27T05:34:27+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/swe-bench-swe-bench","markdown_url":"https://www.graphcanon.com/tools/swe-bench-swe-bench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/swe-bench-swe-bench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=swe-bench-swe-bench","shared_categories":["evaluation-observability"]},{"slug":"eth-sri-lmql","name":"lmql","tagline":"A language for constraint-guided and efficient LLM programming.","github_url":"https://github.com/eth-sri/lmql","owner":"eth-sri","repo":"lmql","owner_avatar_url":"https://avatars.githubusercontent.com/u/5363413?v=4","primary_language":"Python","stars":4203,"forks":221,"topics":["chatgpt","huggingface","language-model","programming-language"],"archived":false,"github_pushed_at":"2025-05-22T07:32:31+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/eth-sri-lmql","markdown_url":"https://www.graphcanon.com/tools/eth-sri-lmql.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eth-sri-lmql","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eth-sri-lmql","shared_categories":[]},{"slug":"openai-human-eval","name":"human-eval","tagline":"Evaluating Large Language Models Trained on Code","github_url":"https://github.com/openai/human-eval","owner":"openai","repo":"human-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/14957082?v=4","primary_language":"Python","stars":3331,"forks":452,"topics":[],"archived":false,"github_pushed_at":"2025-01-17T18:22:17+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/openai-human-eval","markdown_url":"https://www.graphcanon.com/tools/openai-human-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openai-human-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openai-human-eval","shared_categories":["evaluation-observability"]},{"slug":"code-yeongyu-lazycodex","name":"lazycodex","tagline":"Agent harness for complex codebases with project memory and execution planning","github_url":"https://github.com/code-yeongyu/lazycodex","owner":"code-yeongyu","repo":"lazycodex","owner_avatar_url":"https://avatars.githubusercontent.com/u/11153873?v=4","primary_language":"TypeScript","stars":3189,"forks":198,"topics":["ai","ai-agents","claude","claude-code","cli","codex","developer-tools","lazy","lazycodex","oh-my-openagent","omo","openai","orchestration","typescript"],"archived":false,"github_pushed_at":"2026-08-09T08:51:31+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/code-yeongyu-lazycodex","markdown_url":"https://www.graphcanon.com/tools/code-yeongyu-lazycodex.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/code-yeongyu-lazycodex","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=code-yeongyu-lazycodex","shared_categories":[]},{"slug":"salesforce-codet5","name":"CodeT5","tagline":"Home of CodeT5: Open Code LLMs for Code Understanding and Generation","github_url":"https://github.com/salesforce/CodeT5","owner":"salesforce","repo":"CodeT5","owner_avatar_url":"https://avatars.githubusercontent.com/u/453694?v=4","primary_language":"Python","stars":3098,"forks":487,"topics":["code-generation","code-intelligence","code-understanding","language-model","large-language-models"],"archived":true,"github_pushed_at":"2026-06-25T16:27:18+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/salesforce-codet5","markdown_url":"https://www.graphcanon.com/tools/salesforce-codet5.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/salesforce-codet5","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=salesforce-codet5","shared_categories":[]},{"slug":"evalplus-evalplus","name":"evalplus","tagline":"Rigorous evaluation of LLM-synthesized code","github_url":"https://github.com/evalplus/evalplus","owner":"evalplus","repo":"evalplus","owner_avatar_url":"https://avatars.githubusercontent.com/u/132106461?v=4","primary_language":"Python","stars":1794,"forks":205,"topics":["benchmark","chatgpt","efficiency","gpt-4","large-language-models","program-synthesis","testing"],"archived":false,"github_pushed_at":"2025-10-02T22:56:38+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/evalplus-evalplus","markdown_url":"https://www.graphcanon.com/tools/evalplus-evalplus.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evalplus-evalplus","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evalplus-evalplus","shared_categories":["evaluation-observability"]},{"slug":"lean-dojo-leancopilot","name":"LeanCopilot","tagline":"LLMs as Copilots for Theorem Proving in Lean","github_url":"https://github.com/lean-dojo/LeanCopilot","owner":"lean-dojo","repo":"LeanCopilot","owner_avatar_url":"https://avatars.githubusercontent.com/u/136513911?v=4","primary_language":"C++","stars":1314,"forks":127,"topics":["formal-mathematics","lean","lean4","llm","llm-inference","machine-learning","theorem-proving"],"archived":false,"github_pushed_at":"2026-08-22T02:14:29+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/lean-dojo-leancopilot","markdown_url":"https://www.graphcanon.com/tools/lean-dojo-leancopilot.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lean-dojo-leancopilot","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lean-dojo-leancopilot","shared_categories":[]},{"slug":"huybery-awesome-code-llm","name":"Awesome-Code-LLM","tagline":"👨💻 An awesome and curated list of best code-LLM for research.","github_url":"https://github.com/huybery/Awesome-Code-LLM","owner":"huybery","repo":"Awesome-Code-LLM","owner_avatar_url":"https://avatars.githubusercontent.com/u/13436140?v=4","primary_language":null,"stars":1291,"forks":74,"topics":["awesome","code-generation","large-language-models"],"archived":false,"github_pushed_at":"2024-12-10T08:10:54+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/huybery-awesome-code-llm","markdown_url":"https://www.graphcanon.com/tools/huybery-awesome-code-llm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huybery-awesome-code-llm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huybery-awesome-code-llm","shared_categories":["evaluation-observability"]},{"slug":"bigcode-project-bigcode-evaluation-harness","name":"bigcode-evaluation-harness","tagline":"A framework for evaluating autoregressive code generation language models.","github_url":"https://github.com/bigcode-project/bigcode-evaluation-harness","owner":"bigcode-project","repo":"bigcode-evaluation-harness","owner_avatar_url":"https://avatars.githubusercontent.com/u/110470554?v=4","primary_language":"Python","stars":1055,"forks":261,"topics":[],"archived":false,"github_pushed_at":"2025-07-22T13:18:09+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/bigcode-project-bigcode-evaluation-harness","markdown_url":"https://www.graphcanon.com/tools/bigcode-project-bigcode-evaluation-harness.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bigcode-project-bigcode-evaluation-harness","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bigcode-project-bigcode-evaluation-harness","shared_categories":["evaluation-observability"]}]}}