How many bugs can LMs find & fix in large codebases?
Repository Index
47,133 repositories indexed
721–744 of 972 · Most stars
Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
- autoregressive-video-generation
- diffusion
- physics-plausibility
- video-generation
A desktop app where AI agents decompile the games you own into C/C++ that rebuilds them byte for byte.
- ai
- artificial-intelligence
- artificialintelligence
- decompilation
RAFCON (RMC advanced flow control) uses hierarchical state machines, featuring concurrent state execution, to represent robot programs. It ships with a graphical user interface supporting the creation of state machines and contains IDE like debugging mechanisms. Alternatively, state machines can programmatically be generated using RAFCON's API.
- robotics
- graphical-programming
- state-machine
An autonomous agent that profiles, optimizes, and validates AI training code.
Your own Google TV home screen and phone remote, with an optional Claude assistant. Set it up by handing this repo to your AI agent.
- android-tv
- claude-code
- google-tv
- home-screen
Statistical NLG for spoken dialogue systems
- natural-language-generation
- dialogue
- seq2seq
- python
Sippy B2BUA is a RFC3261-compliant Session Initiation Protocol (SIP) stack and Back-to-back user agent (B2BUA) server software.
TranslatedAn Agent programming Harness engineering framework, from requirement clarification to trusted delivery
- code-intelligence
- coding-agents
- developer-tools
- knowledge-management
TranslatedAn agent development practice room based on LangGraph subgraphs: requirement clarification, user notes, document generation, and human review.
DynaFlow: Learning Free-Form Multi-Agent Orchestration
Medical LLM agent and MRI segmentation workspace built on PharmaLLM, with LangGraph, vLLM, and BEU-Net.
A micro neural network multilayer perceptron for MicroPython (used on ESP32 and Pycom modules)
- micropython
- neural-network
- multilayer-perceptron
- mlp
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
A reusable agent skill and Markdown standard for consistent, current project context.
A set of helpers for baking your Django Wagtail site out as flat files.
SuperGhidra: Autonomous Agent Reverse Engineering, Lock-Free Ghidra Daemon & C++ Recovery Suite
- arm64
- binary-analysis
- decompiler
- disassembler
TranslatedCurated agent skills for social media: Xiaohongshu (RedNote), Douyin, WeChat, X, YouTube, TikTok and LinkedIn. Also covers self-media operations, including WeChat Official Accounts, WeChat Channels and Bilibili: topic selection, writing, images, publishing and data. Usable by agents such as 千问 (Qianwen, "Thousand Questions"), 豆包 (Doubao, "bun"), 龙虾 (Longxia, "lobster") OpenClaw, WorkBuddy, Claude Code and Codex.
Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis)
- agent-memory
- ai
- bitemporal
- graphiti
CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.
- clean-room-reimplementation
- ai-agents
- behavioral-testing
- black-box-testing
Watchtower | Self-hosted AI security assessment, asset intelligence, and evidence workflows.
- ai-agents
- attack-surface-management
- docker
- penetration-testing
Implementation of the paper -> https://arxiv.org/abs/1709.00155. For converting information present in the form of structured data into natural language text
Offline evidence-policy checker for PandaSI.
Evidence-grounded multi-agent fundamental research and fact-audit system for A-share listed companies.