Factorly

A local runtime for AI agent tool chains that wraps MCP servers, REST APIs and CLI commands behind one configuration, injects credentials from an encrypted vault, and logs every call.

Visit website factorly.com

Factorly manages tool calls for an AI agent from a local runtime: it wraps MCP servers, REST APIs and CLI commands behind a single configuration, one web UI and one audit log, enforcing governance rules along the way. Credentials are injected from an encrypted vault at call time, so the agent only ever sees a tool's response and never the underlying secret.

An existing MCP server can be wrapped and made callable through Factorly with a single command, and the agent then connects to Factorly itself as one MCP server or CLI that exposes every configured tool. Factorly ships more than 40 blueprints, supports composing workflows with per-step policies and deterministic sequences, and can be installed through Homebrew, npm, pip or Go.

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