Sage
An extensible framework for custom, self-evolving AI agents, with configurable agent packages, tools, skills, and multi-round recursive self-improvement (RSI).
What is Sage?
An extensible framework for custom, self-evolving AI agents, with configurable agent packages, tools, skills, and multi-round recursive self-improvement (RSI).
Overview of Sage
What it is
Sage is an open-source platform for building custom, self-evolving AI agents. It allows defining agent packages, evaluating them, and improving them through multiple rounds of Recursive Self-Improvement (RSI) with version history and choice of which version to adopt. It is licensed under MIT.
Key features
- Custom Agent packages: Define agent instructions, skills, tools, and runtime configuration in sage.yaml; reuse packages in Desktop, Server, or Python applications.
- Self-evolution with RSI: Test and refine packages over configurable rounds using evaluation, tuning, and review agents in separate sessions. Retain every iteration and choose which version to use.
- Plugin-based architecture: Compose model, memory, storage, tool, and scheduling providers with explicit contracts and managed lifecycles.
- Native streaming UI (Desktop 2.1): Uses OpenUI parser with Sage’s Flutter Glass renderer. Supports 31 native component types, light/dark themes, and local calculations.
- Stateful, interactive execution: Durable session history, streamed events, and pause/resume with human input and approvals.
- Multi-agent orchestration: Coordinate Studio members through directed messages or compose Agent Flows in the runtime.
- Extensible tool ecosystem: Bring built-in tools, reusable Skills, and MCP services into the same agent workflow.
- One runtime, multiple hosts: Use SAgents v2 through Desktop and Server, or embed in Python applications.
Use cases
- Building custom AI agents with specific instructions, skills, and tools.
- Self-improving agents that can be iteratively optimized through RSI rounds.
- Multi-agent coordination for complex tasks.
- Interactive desktop applications with streaming UI and local calculations.
- Server-based multi-user web access with Agent Studio.
Getting started
Desktop from source (requires Python 3.12+ and Flutter with Dart ^3.12.2): bash git clone https://github.com/ZHangZHengEric/Sage.git cd Sage python3.12 -m venv .venv source .venv/bin/activate python -m pip install -e . cd app/v2/desktop flutter pub get flutter run -d macos Server from source (requires Python 3.12+, MySQL, Node.js 22.12+): bash python -m pip install -e '.[server-v2]' cp app/v2/server/.env.example app/v2/server/.env Set MySQL connection, JWT secret, and admin credentials in .env, then: bash cd app/v2/server/web npm install npm run build cd ../../.. python -m app.v2.server Open localhost:8090. For a quick Python agent without sage.yaml, see the repository README for the quickstart.py example.
License and pricing
License: MIT. Pricing: open source (free).
Based on the project's public README and repository metadata.