GitHub 2026-02-11 Daily Trending Projects

LangExtract is a Python library for production and research that uses LLMs and example-driven constraints to turn unstructured text into source-grounded, auditable structured data, with interactive HTML visualization for human review and large-scale document workflows.

AionUi is a cross-platform, local-first visual Cowork platform for multiple CLI AI tools, unifying models and sessions for batch file operations and real-time previews; suited for privacy-conscious AI office automation.

Shannon is a white‑box autonomous AI pentester that, from source‑aware analysis, constructs and executes real exploit PoCs and produces reproducible reports—enabling security and development teams to move pentesting from a yearly event to a continuous process.

GitHub Agentic Workflows enables natural-language Markdown definitions of AI agentic workflows run in GitHub Actions with layered guardrails for controlled repository automation; evaluate license, community maturity, and auditability before production deployment.

A Claude Code-focused compound-engineering plugin and CLI that defines cyclic workflows, exposes a plugin marketplace, and offers experimental OpenCode/Codex conversions; suitable for engineering teams with self-managed tooling to trial in controlled environments.

A Chinese-focused multi-agent LLM financial decision framework integrating multi-vendor models and A/HK/US data—well suited for research and enterprise prototyping but requires careful review of license, maintenance, and production/compliance risks.

GitButler uses virtual branches to manage multiple uncommitted changes in a single working directory, simplifying splitting, pushing and review workflows with AI-assisted commits and a cross-platform desktop client — targeted at developers and teams needing parallel context management and higher multitasking efficiency.

An interactive course for Product Managers demonstrating Claude Code AI workflows to speed document handling, PRD creation, and data-driven analysis—practical, module-based guidance for PMs integrating AI into daily product work.

Aggregates numerous LLM application examples and links with emphasis on Agents and RAG practices; well suited for learning, comparison and rapid prototyping, but users should watch entry quality and maintenance stability.

drawDB offers no-login, in-browser visual ER editing and SQL export for small teams and teaching; license and maintenance require evaluation.

Monty: Rust minimal secure Python VM for safe LLM code execution.

free-llm-api-resources compiles free or trial LLM API providers with model and quota details to enable fast evaluation and prototyping for cost-conscious developers and researchers; verify license and data-use terms before production use.

Claude‑skills supplies 66 specialized skills and 9 workflows for Claude‑based conversational programming, emphasizing context engineering and progressive disclosure—ideal for full‑stack teams using Claude as an expert pair programmer; however, there are no formal releases and contributor activity is low, so evaluate maintenance and compatibility risks before adoption.

Dexter is an autonomous multi-agent system designed for professional financial research that plans and executes data retrieval, computation, and self-validation—suitable for quant research and enterprise finance automation.