12 open-source projects share topics or a category with magic. Each comparison below is drawn from recorded GitHub metadata — language, license, activity and review status. None of them is a judgement about which is better for you.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Choose dify if…
you want something your agent can install directly rather than a library to wire up yourself
you want the more widely starred option (161.1k)
you specifically need agentic-ai or agentic-framework
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
Choose cursor-talk-to-figma-mcp if…
you would rather work in JavaScript than TypeScript
you need a detected license — this one reports MIT License
you specifically need agentic or agentic-ai
Shares agent, ai, llm, mcp with magic.
Last push 4 months ago.MIT LicenseJavaScript7.1k+23
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Choose MemOS if…
you need a detected license — this one reports Apache License 2.0
you want something your agent can install directly rather than a library to wire up yourself
you want the more widely starred option (12.4k)
you specifically need agentic-ai or ai-agents
Shares agent, ai, llm, mcp with magic.
Pushed 2 days ago.Apache License 2.0TypeScript12.4k
BISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration.
Choose bisheng if…
you would rather work in Python than TypeScript
you need a detected license — this one reports Apache License 2.0
you want something your agent can install directly rather than a library to wire up yourself
Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.
