Search

AI agent for GitHub repo/account insights

An open-source, self-evolving AI agent whose reasoning core is an LLM-Fusion engine (panel -> judge -> synthesizer).

Core abstractions for Agentivium agent-native systems.

Reusable runtime core for durable agent applications.

AI Agent 红队安全测试平台 — 从 CLI 到 Dashboard

Vector Vein inspired agent framework with cycle runtime, tools and memory management

Multi-LLM planning & orchestration that routes work across the terminal AI CLIs you already have: plan -> phases -> tasks, model choosable per role and per task.

No description available

TaxSentry is a provider-first local AI agent with a friendly setup wizard, persistent memory, and cross-platform TUI.

Zero dependency, zero build framework core for agents building AI-friendly web applications.

Dev-only on-screen annotation tool: scribble on the live page, take an OS screenshot, upload it for an AI agent to read.

Reserved: agentcradle — a platform for building agentic chatbot apps. Template repo coming soon.

Read, transform, and write AI agent session logs across formats

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...

TypeScript SDK for AI agents to take and repay revenue-underwritten credit on TrustLine (Stellar). Settles in USDC.

Bring Claude Code to Visual Studio 2026: a native diff with accept/reject, a live debugger Claude can drive, Roslyn code navigation, and Test Explorer integration. The IDE half of Claude Code's integration protocol. Community-built, unofficial.

An open-source operating system for Claude Code - persistent Obsidian-vault memory, an /open + /close session rhythm, a subagent Pantheon, context hooks, and background daemons. Markdown + shell, no database, no build step. MIT.

A reasoning-first idle engine for persistent LLM agents. Behaviour emerges from the agent reasoning about its idle state, gated by a cheap model-free safety layer.

Does your CLAUDE.md actually do anything? Trap-test your agent rules in isolated sessions and get honest deltas.