SWE-chat: Coding Agent Interactions From Real Users in the Wild

Detect vulnerable regexes in your project. REDOS, catastrophic backtracking.

Codebase of the paper "Towards Automated Page Object Generation using Large Language Models" (ICST 2026)

WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements

When Semantic Caches Lie: measuring false hits, downstream cost, and calibration in embedding-based LLM caches. Cache-equivalence is not cosine similarity. CPU-only, deterministic reproduction of e…

Detect and patch vulnerabilities in AI-generated Python code — VS Code extension

Knowledge Graphs and Semantic Search for Python Repositories using Neo4j

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

This is a continuously updated handbook for readers to easily track the latest Text-to-SQL techniques in the literature and provide practical guidance for researchers and practitioners.

Open-source framework for superagents.

Agent memory infrastructure built around context economics. Memories disclose handle → summary → full → sources. Skills auto-memorise the conversation; MCP gives the agent explicit recall.

AI citation hallucination detector — verify .bib files against CrossRef, Semantic Scholar, OpenAlex. Claude Code skill.

🦡 codebadger is a containerized Model Context Protocol (MCP) server that gives AI agents and LLMs deep, queryable access to a codebase's structure and data flow through Joern Code Property Graphs (…

Scarf CLI

WybeCoder Verified Generation of Imperative Code with LLMs

Agent harness to publish your agent chat history as Huggingface datasets.

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Give Claude Code a subconscious

Self-referential self-improving agents that can optimize for any computable task

8-step pipeline for evaluating PhD research ideas to top-3 finance journal quality. Works with any AI coding assistant.

Sourcerer's Code Clone project

A dataset of optimization commits.

Citation Extraction & Reference Checking Assistant

An agentic skills framework & software development methodology that works.

Analyze AI agent trajectories: extract actions, summarize, embed, and visualize.

SWE-bench evaluation framework demonstrating multi-model consultation improves accuracy