deepagents vs declarative-agents
LLM agent frameworks compared
deepagents and declarative-agents both help developers build tool-augmented LLM agents. deepagents provides a Python harness with planning and agent capabilities built in, while declarative-agents uses YAML profiles interpreted by a shared Go runtime.
deepagents: Build Agents with Planning and Tooling Built In
Deep Agents is a Python agent harness for building LLM agents with planning, delegation, file access, and context management built in. It suits developers who need a more capable starting point than a minimal agent loop, while retaining control over models and tools.
declarative-agents: Define LLM Agents with YAML Profiles
Nokia Bell Labs' declarative-agents uses YAML profiles and a Go runtime to define and execute tool-augmented LLM agents. It suits teams that want to change agent workflows through configuration rather than rebuild a binary.
| deepagents | declarative-agents | |
|---|---|---|
| Language | Python | Go |
| License | MIT | BSD-3-Clause |
| Stars | 29.9k | 5 |
| Forks | 4.2k | 2 |
| Last analyzed | Oct 3, 2026 | Oct 24, 2026 |
Key differences
- deepagents is a Python harness built on LangGraph; declarative-agents is a Go runtime for profile-defined state machines.
- deepagents bundles planning, file operations, sub-agent delegation, and context management; declarative-agents focuses on defining tools, states, transitions, signals, and budgets in YAML.
- deepagents supports customization of its components and tools; declarative-agents emphasizes reusable agent and tool blocks, application compositions, and a documented DSL.
- deepagents is licensed under MIT; declarative-agents is licensed under BSD-3-Clause.
- deepagents is designed for production deployments on LangGraph, with tracing, evaluation, and monitoring paired with LangSmith; declarative-agents is in maintenance mode and accepts bug fixes only.
- deepagents has 29.9k stars and 4.2k forks; declarative-agents has 4 stars and 1 fork, which indicates limited visible GitHub adoption but does not establish quality or support levels.
Choose deepagents if you…
- need built-in planning, file and shell tools, sub-agent delegation, or context management in a Python harness.
- want to customize an agent structure built on LangGraph while retaining control over models and tools.
- are building workflows that benefit from persistent state or human approval steps for tool calls.
Choose declarative-agents if you…
- want to change agent workflows through YAML profiles without changing the runtime binary.
- need a Go runtime with reusable agent and tool definitions, configuration validation, and documented design patterns.
- want to start from an included chatbot-mesh or planner-executor-critic coding-agent composition.
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.