DISCOVER THE FUTURE OF AI AGENTS

All Projects

10 projects

Axe

A lightweight CLI tool for managing and running single-responsibility LLM agents via declarative TOML configuration, featuring sub-agent delegation, stdin piping, persistent memory, and MCP tool support.

Model & Inference FrameworkMulti-Agent SystemModel Context Protocol

IronClaw

An Agent OS focused on privacy, security and extensibility, providing an always-available personal AI assistant through WASM-sandboxed execution, multi-channel access, and persistent memory.

Model Context ProtocolAI AgentsRust

OneCLI

The open-source secret vault and secure gateway for AI agents, enabling transparent interception and zero-touch key injection.

Model Context ProtocolAI AgentsNext.js

Moltis

A secure persistent personal AI agent server delivered as a single Rust binary, supporting 20+ LLM providers, 9 communication channels, sandboxed execution, and hybrid memory search.

Model & Inference FrameworkRAGModel Context Protocol

Zorai

A durable, multi-agent, auditable, and learnable AI execution platform built on a daemon-first architecture, enabling seamless cross-terminal switching and long-running autonomous tasks.

Docs, Tutorials & ResourcesAI AgentsModel Context Protocol

MCP Toolbox for Databases

An enterprise-grade open-source MCP server by Google, supporting unified access, NL2SQL, and security control for 20+ databases, acting as a middleware control plane connecting AI agents and IDEs directly to enterprise databases.

Natural Language ProcessingAI AgentsModel Context Protocol

cursor2api

An unofficial reverse-proxy tool that converts Cursor's free doc-page AI chat endpoint into Anthropic Messages API and OpenAI Chat Completions API, featuring identity protection, refusal interception, cognitive reconstruction, context compression, and anti-truncation mechanisms for Claude Code, Cursor IDE, and various third-party clients.

Model & Inference FrameworkSDKLarge Language Models

Pipelock

Open-source AI Agent egress firewall providing OS-level sandboxing, 11-layer URL scanning, and prompt-injection response detection for MCP and agentic workflows.

Model Context ProtocolAI AgentsRust

OpenJarvis

A local-first personal AI agent framework from Stanford that enables offline agent orchestration, skill import, and trace-driven continuous learning through five composable primitives, supporting 10+ inference backends and four interaction modes.

OtherLarge Language ModelsModel Context Protocol

mcp-scan

Security scanner for AI Agents and MCP servers. Detects prompt injection, tool poisoning, and data leakage; features runtime proxy protection and CI/CD integration.

AI AgentsModel Context ProtocolPython
Per page

Page 1 / 1 · 10 total

STAY UPDATED

Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.