autogen vs declarative-agents
Multi-agent AI frameworks compared
autogen and declarative-agents both support building tool-augmented agent workflows. autogen provides layered Python APIs for multi-agent applications, while declarative-agents uses a Go runtime to interpret workflows defined in YAML profiles.
autogen: Build Multi-Agent AI Applications
AutoGen is a Python framework for building AI agents that work independently or alongside people. It supports multi-agent orchestration, model and tool integrations, and prototyping, but is now in maintenance mode.
declarative-agents: Define Tool-Augmented Agents in YAML
A Go runtime interprets YAML profiles that define agent tools, states, transitions, and budgets. It suits teams that want to change agent workflows through configuration, though the project is new, contributor-concentrated, and in bug-fix-only maintenance mode.
| autogen | declarative-agents | |
|---|---|---|
| Language | Python | Go |
| License | CC-BY-4.0 | BSD-3-Clause |
| Stars | 61.3k | 4 |
| Forks | 9.3k | 1 |
| Last analyzed | Oct 3, 2026 | Oct 11, 2026 |
Key differences
- autogen offers event-driven agents, higher-level chat patterns, model integrations, and prototyping tools; declarative-agents centers on configurable state-machine workflows described in YAML.
- autogen is written in Python and licensed under CC-BY-4.0; declarative-agents is written in Go and licensed under BSD-3-Clause.
- autogen includes AutoGen Studio for prototyping and demonstrations, while declarative-agents provides reusable blocks, example applications, a DSL specification, and design-pattern documentation.
- autogen is in maintenance mode with bug fixes, security patches, and documentation improvements; declarative-agents also limits maintenance to bug fixes.
- autogen has 61.3k stars and 9.3k forks; declarative-agents has 4 stars and 1 fork, with work concentrated in one contributor.
Choose autogen if you…
- need to maintain or migrate an existing AutoGen application.
- want Python APIs for multi-agent orchestration, model integrations, or MCP tools.
- want to prototype workflows with AutoGen Studio or evaluate them with AutoGen Bench.
Choose declarative-agents if you…
- want to define agent states, transitions, tools, and budgets in YAML.
- need a Go runtime that interprets configurable agent profiles.
- want reusable agent and tool blocks, runnable examples, and a normative application DSL specification.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.