MaximeRobeyns / self_improving_coding_agent
A coding agent framework, that works on its own codebase.
☆28Updated 2 weeks ago
Alternatives and similar repositories for self_improving_coding_agent
Users that are interested in self_improving_coding_agent are comparing it to the libraries listed below
Sorting:
- Agentic Knowledgeable Self-awareness☆56Updated 3 weeks ago
- Cerebrum: Agent SDK for AIOS☆54Updated 2 weeks ago
- This repository contains popular code generation frameworks such as MapCoder, CodeSIM.☆45Updated 3 weeks ago
- Official Repo for The Paper "Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems"☆51Updated 2 months ago
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆53Updated last month
- accompanying material for sleep-time compute paper☆82Updated last week
- Open Agent Computer Interface☆68Updated 5 months ago
- [NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications☆75Updated last week
- Challenges for general-purpose web-browsing AI agents☆48Updated this week
- ☆64Updated last month
- Official code repository for Sketch-of-Thought (SoT)☆112Updated this week
- From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging☆71Updated last month
- Very minimal (and stateless) agent framework☆43Updated 4 months ago
- Code for ScribeAgent paper☆57Updated 2 months ago
- LLM reads a paper and produce a working prototype☆56Updated last month
- Framework and toolkits for building and evaluating collaborative agents that can work together with humans.☆76Updated last month
- The Library for LLM-based multi-agent applications☆80Updated 2 months ago
- ☆64Updated 8 months ago
- ☆28Updated last year
- ☆50Updated 5 months ago
- ☆41Updated 4 months ago
- AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reaso…☆103Updated last month
- Source code for our paper: "SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals".☆65Updated 10 months ago
- Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆90Updated 2 months ago
- Agent computer interface for AI software engineer.☆70Updated last week
- ☆27Updated last month
- Code for the paper: CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models☆19Updated last month
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆96Updated 6 months ago
- ☆21Updated 6 months ago
- The official repo for the code and data of paper SMART☆26Updated 2 months ago