8 Best Voyager Alternatives in 2026 (Open Source)
Voyager — An Open-Ended Embodied Agent with Large Language Models. First LLM-powered embodied agent that continuously explores, acquires skills as reusable code, and demonstrates lifelong learning in an open-world environment — 3.3x more unique items and 15.3x faster milestone achievement vs prior SOTA
These 8 open-source tools do the same job. They are ordered by how closely they match Voyager, with live GitHub data so you can see which projects are actively maintained.
| Tool | GitHub stars | Stars / 30d | Last commit |
|---|---|---|---|
| Voyager(original) | 7.2k | +73 | 2023-07-27 |
| Codel | 2.5k | +4 | 2024-04-05 |
| AutoAct | 239 | +0 | 2025-01-13 |
| CodeAct | 1.7k | +11 | 2024-05-23 |
| TaskWeaver | 6.2k | +6 | 2026-03-23 |
| AI Legion | 1.4k | +1 | 2025-05-27 |
| CAMEL | 17.8k | +207 | 2026-09-30 |
| Agentflow | 321 | +0 | 2023-08-11 |
| openvibe | 1.4k | +-1 | 2026-07-03 |
1. Codel
✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.
What sets it apart: vs Open Interpreter / ChatDev: automatic Docker image selection per task + integrated browser + editor in one autonomous agent — fully sandboxed execution with local LLM support via Ollama
Best for: Autonomous development tasks in sandboxed environments; Complex multi-step project automation; Web research integrated with code editing workflows
2. AutoAct
[ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning
What sets it apart: vs ReAct/Reflexion/BOLAA: division-of-labor strategy automatically creates specialized Plan/Tool/Reflect sub-agents from self-synthesized trajectories — zero dependency on closed-source model data or human annotations
Best for: Research on automatic agent learning without GPT-4 dependency; Multi-hop QA requiring complex question decomposition; Teams wanting to train specialized sub-agents from self-generated data
3. CodeAct
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.
What sets it apart: vs ReAct/text-based agents: executable Python code as unified action space with containerized execution, achieving 20% higher success rate than JSON/text actions
Best for: Research on code-based agent action spaces; Building agents that execute Python code as their primary action mechanism
4. TaskWeaver
The first "code-first" agent framework for seamlessly planning and executing data analytics tasks.
What sets it apart: Unlike text-only agent frameworks like AutoGen, TaskWeaver preserves full code execution state and in-memory data across turns, enabling seamless multi-step data analytics that manipulate DataFrames and complex structures directly
Best for: Data scientists needing automated multi-step analytics pipelines with code generation; Teams building AI agents that must handle complex data structures like DataFrames natively
5. AI Legion
An LLM-powered autonomous agent platform
What sets it apart: Multi-agent platform where autonomous LLM agents with persistent memory collaborate through console interaction, learning from their own mistakes
Best for: multi-agent-experimentation; exploring-agent-self-organization; autonomous-task-delegation
6. CAMEL
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
What sets it apart: Purpose-built for studying agent scaling laws with million-agent simulation support — vs other frameworks focused on practical deployment
Best for: Research on multi-agent collaboration and emergent behaviors; Synthetic data generation for model training
7. Agentflow
Complex LLM Workflows from Simple JSON.
What sets it apart: vs AutoGPT / LangChain agents: deterministic step-by-step workflow execution from JSON definitions — balanced between chat flexibility and autonomous agent unpredictability, with custom function support
Best for: Developers wanting structured, repeatable LLM workflows vs. freeform chat; Multi-step content generation pipelines (e.g., market research → analysis → report); Teams needing predictable LLM execution with human-readable workflow definitions
8. openvibe
Modular Auto-GPT Framework
What sets it apart: vs Auto-GPT: proper Python package with full state serialization and GPT-3.5 optimization — save and resume agent sessions without external databases, works well without GPT-4
Best for: Developers wanting a modular, Pythonic alternative to Auto-GPT; GPT-3.5 users wanting autonomous agent capabilities without GPT-4; Teams needing agent state persistence (save/resume sessions)