Semia
Semia, security audit for AI agent skills.
An AI agent is a program that uses a language model to decide what to do next, calls tools such as a browser, a code interpreter or an API, and repeats until the task is done. The projects here range from frameworks for building your own agents to finished agents that write code, browse the web or run business workflows.
Compare three things. Which models it can use: a single provider, or any OpenAI-compatible endpoint including local ones. How it limits what the agent may do: sandboxing, approval steps and permission lists. And whether it keeps memory between steps and sessions. An agent that runs code or shell commands should run in a sandbox, so check that before giving it access to your machine.
Semia, security audit for AI agent skills.
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
EMNLP 2026 Main Conference Paper: MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems (https://arxiv.org/abs/2601.14230)
Span-level grounding verification for RAG, code, and tool-grounded AI outputs.
TimeCopilot: the GenAI Forecasting Agent. Built on LLMs and Time Series Foundation Models, it lets you forecast, cross-validate, and detect anomalies using multiple foundation models through a single API. From finance and energy to web analytics, TimeCopilot turns natural-language queries into production-ready forecasts.
Open-source 2D IDE for managing AI agents in native CLIs, terminal, gits, beads issues, and files across multiple projects and machines. Self-host on a single machine via localhost OR host on a cluster via Tailscale OR connect to app.49agents.com (coming soon)
Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for calling more than 200+ LLMs.
A MCP (Model Context Protocol) server for interacting with dbt.
Emergence World: A world designed to reveal what no benchmark can: emergent intelligence.
Fable 5.1 orchestrates. GPT-5.6 Luna and DeepSeek V4 Flash implement.
cmux: tmux for Claude Code
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.
"Aurogen🍊: The Multi-Agent Evolution of OpenClaw."
Control Figma from the command line. Full read/write access for AI agents — create shapes, text, components, set styles, export images. 100+ commands.
Fantasy Premier League Kotlin/Compose Multiplatform sample
Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context
An open-source AI assistant framework like openclaw
AI pair programming in your terminal — one static binary, sub-ms startup, any model
Figma Plugin & MCP server to bypass API limits
bkit Vibecoding Kit - PDCA methodology + Claude Code mastery for AI-native development
Zero-config goal-to-tasks engine for Claude Code (the Atlas engine). Graded PRD validation, dependency-ordered task graph, evidence-gated execution.
[ICLR 2026] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation