AgentVoy

A CLI tool and SDK that scaffolds and deploys AI agent projects across several frameworks -- OpenAI, Anthropic, CrewAI, LangGraph, Google ADK, LlamaIndex and AutoGen -- with built-in guardrails and security defaults.

Agent frameworks

Visit website agentvoy.com

AgentVoy asks upfront whether to build a local "Agent" project (a flat structure with an interactive REPL for fast development) or a deployable "App" (a FastAPI server, Streamlit chat UI, Docker and cloud configs), and can scaffold sequential multi-agent pipelines such as a researcher-writer-reviewer chain.

App-mode projects include a DevTools dashboard with real-time WebSocket trace streaming of agent events such as LLM calls, tool calls and guard checks, plus a payload inspector for tokens and latency.

Every generated project ships with a guardrails and permissions configuration file from the start, and it installs and runs through npx agentvoy.

More in Agent frameworks

See all 902

Recurse
recurse.run
A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.
- Agent frameworks
ProofForge
shulgin.is-a.dev
An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.
- Agent frameworks
local-coder
github.com
Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.
- Coding agents
- Agent frameworks

More in Agent frameworks

Recurse

ProofForge

local-coder

Cookies