microsoft / monitors4codegenLinks
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to build applications around language servers.
☆262Updated 10 months ago
Alternatives and similar repositories for monitors4codegen
Users that are interested in monitors4codegen are comparing it to the libraries listed below
Sorting:
- multilspy is a lsp client library in Python intended to be used to build applications around language servers.☆354Updated 2 weeks ago
- Grep source code and see useful code context about matching lines☆248Updated last month
- Binary Python wheels for all tree sitter languages.☆227Updated 4 months ago
- Extract and combine multiple source code views using tree-sitter☆140Updated last month
- Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions☆43Updated 10 months ago
- A tree-sitter language pack☆146Updated this week
- Enhancing AI Software Engineering with Repository-level Code Graph☆184Updated 2 months ago
- ✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024☆167Updated 10 months ago
- [NeurIPS'24] SelfCodeAlign: Self-Alignment for Code Generation☆306Updated 4 months ago
- CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)☆143Updated 10 months ago
- RepoQA: Evaluating Long-Context Code Understanding☆109Updated 7 months ago
- Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.☆186Updated this week
- [NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898☆220Updated last year
- Scaling Data for SWE-agents☆256Updated this week
- Fast and robust AST parsing of any language☆43Updated 5 months ago
- ☆445Updated this week
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.☆228Updated last week
- EvoEval: Evolving Coding Benchmarks via LLM☆73Updated last year
- [FORGE 2025] Graph-based method for end-to-end code completion with context awareness on repository☆63Updated 9 months ago
- Construct graphs from parsed source code☆267Updated 6 months ago
- A multi-programming language benchmark for LLMs☆254Updated this week
- A benchmark for LLMs on complicated tasks in the terminal☆177Updated this week
- A command line tool for parsing code syntax☆132Updated 8 months ago
- CodeSage: Code Representation Learning At Scale (ICLR 2024)☆109Updated 7 months ago
- Multi-language code navigation API in a container☆82Updated last month
- r2e: turn any github repository into a programming agent environment☆125Updated 2 months ago
- ☆158Updated 10 months ago
- Official implementation of paper How to Understand Whole Repository? New SOTA on SWE-bench Lite (21.3%)☆86Updated 3 months ago
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents☆124Updated last year
- A distributed, extensible, secure solution for evaluating machine generated code with unit tests in multiple programming languages.☆55Updated 8 months ago