graphbit vs declarative-agents
Multi-agent AI workflow frameworks compared
graphbit and declarative-agents both help developers build tool-using, multi-step LLM agents. graphbit defines connected workflows through a Python API backed by Rust, while declarative-agents interprets YAML profiles through a Go runtime.

graphbit: Build Type-Safe Multi-Agent AI Workflows
GraphBit is a Rust-core framework with a Python API for building and running multi-agent AI workflows. It suits teams that need concurrent execution, multiple LLM providers, and workflow reliability with Python ergonomics.

declarative-agents: Build Agents from YAML Profiles in Go
Declarative Agents uses YAML profiles and a Go runtime to define and execute tool-augmented LLM agents without encoding each workflow in a separate binary. It suits teams building configurable agent applications, but is now in maintenance mode and depends heavily on one contributor.
| graphbit | declarative-agents | |
|---|---|---|
| Language | Rust | Go |
| License | Apache-2.0 | BSD-3-Clause |
| Stars | 585 | 6 |
| Forks | 120 | 1 |
| Last analyzed | Oct 4, 2026 | Nov 14, 2026 |
Key differences
- graphbit uses graph-based workflows with agent, tool, and custom nodes; declarative-agents models agents through YAML profiles with states, transitions, signals, and budgets.
- graphbit combines a Python API with a Rust engine and supports concurrency, retries, circuit breakers, and workflow tracing; declarative-agents uses a Go runtime with state-machine execution and profile validation.
- graphbit connects to providers including OpenAI, Anthropic, Azure OpenAI, Ollama, and OpenRouter; declarative-agents provides LLM integration and a standard tool library.
- graphbit is licensed under Apache-2.0; declarative-agents is licensed under BSD-3-Clause.
- graphbit is active; declarative-agents is in maintenance mode, with ongoing work limited to bug fixes apart from completed maintainer-approved exceptions.
- graphbit has 585 stars and 120 forks; declarative-agents has 6 stars and 1 fork.
Choose graphbit if you…
- need a Python-facing API backed by a Rust runtime for graph-based agent workflows.
- want concurrency controls, shared workflow state, error recovery, and tracing of LLM calls.
- need to connect workflows to several supported LLM providers.
Choose declarative-agents if you…
- want to define agent tools and transitions in YAML rather than encode each workflow in a separate binary.
- need reusable agent and tool blocks, application examples, or profile validation before serving.
- can work with a project in maintenance mode and its Go and Mage quickstart requirements.
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.