Back to directory

IllusionAgent

An open-source AI agent platform that unifies a multi-provider LLM gateway, a bilingual command-line interface, a browser-based web interface and an extension system into one assistant for Windows, macOS and Linux.

IllusionAgent

IllusionAgent combines a command-line interface and a separate browser-based web interface around a shared multi-provider LLM gateway, so it can talk to Anthropic, OpenAI, Copilot, Codex and other compatible endpoints. It supports specialized built-in sub-agents, two different context-compaction strategies, Model Context Protocol server connections, hooks, plugins, and a scheduler for unattended automation across chat platforms such as Feishu, WeChat and QQ.

Other features include fine-grained permission controls, adjustable reasoning-effort levels, a bilingual Chinese/English interface that switches automatically, and a separate desktop edition built with Electron that bundles its own Python and Node.js runtime with installers for Windows, macOS and Linux.

It is written in Python, requires Python 3.10 or newer, and can be installed from PyPI without needing Node.js.

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.

  • 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.

  • 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.