manifest.build is an open source LLM router for AI agents and related tools. It connects AI agents and harnesses to any provider in seconds, supporting subscription, pay-per-token, local model and custom provider options. The tool offers features including model fallbacks, full request logging, autofix for broken provider calls, an LLM gateway for centralized provider management, and observability tools for tracking usage, reliability and costs. The software is open source, allowing users to self-host it or contribute to its development.
Directory
Search results
Published directory entries matching your search.
Manus is described as an action engine that executes tasks and automates workflows. Its features page lists building web and mobile apps, creating videos, slides and designs, research, and automations. A video feature uses Seedance 2.5 to generate shots, with editable tracks in a Video Editor.
Uses AI agents to complete tasks, coordinate tools or automate multi-step workflows.
TypeScript-native AI agent framework for web developers. Workflow automation with typed tools and integrations. MIT.
Uses AI agents to complete tasks, coordinate tools or automate multi-step workflows.
Open-source governed shared memory for AI agent fleets with cross-agent recall, permissions, audit trails, and persistent memory.
Memory-oriented tooling for AI agents, focused on persistent context, recall, and more structured long-term memory behavior.
Mengram is an open-source project that provides human-like memory capabilities for AI agents. It supports semantic, episodic, and procedural memory types, with experience-driven procedures designed to learn from failures. The project offers a free API, Python and JavaScript SDKs, and integrations with LangChain, CrewAI, and OpenClaw.
PraisonAI is an open-source project hosted on GitHub under the MervinPraison/PraisonAI repository. It enables the deployment of autonomous, self-improving AI agents capable of researching, planning, coding, and executing tasks. The tool includes built-in memory and retrieval-augmented generation (RAG) capabilities, supports over 100 large language models, and can be deployed with 5 lines of code.
MetaGPT is an open-source multi-agent framework hosted on GitHub under the FoundationAgents/MetaGPT repository. It is designed to function as an AI software company system and supports natural language programming capabilities.
The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo.
Microagents is an experimental framework for dynamically creating self-improving agents in response to user tasks. Generated agents are assessed and stored for reuse across chat sessions. It uses Python, OpenAI's GPT-4 Turbo, and Text-Embedding-Ada-002. Agents execute Python code directly and do not currently operate within a sandbox.
Microsoft Agent Framework is a framework for building AI agents and multi-agent workflows in .NET, Python, and Go. It provides agents that use LLMs to process inputs, call tools and MCP servers, and generate responses, plus functional and graph-based workflows that connect agents and functions through explicit execution paths. It includes model clients, agent sessions, context providers, middleware, and MCP clients.
MiMo Studio helps build, test, automate, or manage AI agents, prompts, models, and API workflows.
📦 Open-Source Models (via Nebius).
MindPal is a platform for turning documents, courses and SOPs into AI agents and multi-agent workflows. It is aimed at coaches, consultants, course creators and agencies, and users can publish agents as chatbots, embedded tools or branded portals. It offers no-code building, ready-made templates and free starting use.
MindStudio is a visual platform for designing, building and deploying AI agents without coding, with optional code extensibility. It offers over 100 templates and connects to 200+ AI models. A product agent named Remy, in alpha, builds applications from a shared spec.
MiniMax AI helps build, test, automate, or manage AI agents, prompts, models, and API workflows.
Mistral offers frontier open-weight models that organizations can own and control. Models can be customized with Forge, deployed with Studio, and run on-premises, in a VPC, or in Mistral's cloud. It also provides Vibe, a personal AI agent available on web and mobile.
Mistral Studio helps build, test, automate, or manage AI agents, prompts, models, and API workflows.
MLRun is an open source MLOps platform for building and managing continuous machine learning applications across their lifecycle. It integrates with development and CI/CD environments to automate the delivery of production data, ML pipelines, and online applications.
A Hugging Face Space for a multiplayer online role-playing game that can be explored and played directly in a web browser without downloads. It is described as a place for humans, agents and NPCs to meet.
Speed up your Pandas workflows by changing a single line of code.
An open source, serverless framework for building intelligent agents and APIs in Go or AssemblyScript (a TypeScript-like language).