Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
Repository Index
47,133 repositories indexed
481–504 of 566 · Most stars
TranslatedA Skill based on the McDonald's MCP for benefit actuarial calculation—it checks prices in real time according to the outlet and account benefits, works out whether this meal is worth it and whether this card is worth it, and completes the order with a single confirmation
Agent-first slide decks: comment under a slide, and your coding agent (Claude Code or Codex) makes the change and replies on the slide.
- ai-agents
- claude-code
- codex
- presentations
Let agents control many desktop software directly from the cli, with one pip install, and no MCP servers.
- adobe-after-effects
- adobe-audition
- adobe-illustrator
- claude-code
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.
- agent-framework
- agent-runtime
- agent-skills
- ai-agent
Model-controlled context blocks for DeepSeek Harness PTC mode
- ai-agents
- context-management
- deepseek-harness
- dsh
Curated List of AI, ML and Deep Learning books
A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
- macos
- swift
- automation
- computer-use-agent
A Consistent Data Visualizer for Agents and Humans
Translated养只AI (Raise an AI) — an open-source, all-in-one platform for raising a whale girl. Supports bringing your own model, Bilibili exploration, diary memory, and Feishu interaction.
- ai-companion
- bilibili
- desktop-pet
- digital-life
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
The AI-native browser automation library. Snapshot + ref targeting — born from OpenClaw, built for agents, by agents.
Autonomous multi-agent framework to optimize scientific software
- acceleration
- agentic-ai
- ai-agents
- bioinformatics
CLI tool for running coding agents inside hardware-isolated microVMs
AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.
- ai-agents
- document-processing
- dspy
- entity-extraction
Search the web and primary sources, read full pages, and check every citation. MCP server for Claude, Cursor, Codex and more. Runs on your machine.
Run your coding agents from Telegram. A bridge for Claude Code, Codex, OpenCode, Pi and Antigravity CLI: send tasks by text or voice, watch them work and approve changes from your phone.
- ai-agents
- claude-code
- cli-tools
- codex
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
git checkout for releases that span many repos. Version tags that restore your whole product. No server, no database, any language.
EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.
- ai-agents
- persistent-memory
- mcp
- claude-code
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
- ai-agents
- claude-code
- cli
- context-window
Durable execution framework for AI agents in Go. Keeps agent state, tool calls, and execution loops resilient across process crashes.
- agentic-ai
- ai
- ai-agents
- golang