--- title: "agentscope vs Odyssey" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/agentscope-ai-agentscope-vs-zju-vipa-odyssey" tools: ["agentscope-ai-agentscope", "zju-vipa-odyssey"] --- # agentscope vs Odyssey *GraphCanon updated Jul 11, 2026* ## Verdict Pick agentscope when license: agentscope is Apache-2.0, Odyssey is MIT; pick Odyssey when license: Odyssey is MIT, agentscope is Apache-2.0. [agentscope](https://docs.agentscope.io/) reports 28k GitHub stars, 3.2k forks, and 257 open issues, last pushed Jul 10, 2026. [Odyssey](https://github.com/zju-vipa/Odyssey) has 396 stars, 27 forks, and 2 open issues, last pushed Oct 22, 2025. Figures are from public GitHub metadata via [agentscope's repository](https://github.com/agentscope-ai/agentscope) and [Odyssey's repository](https://github.com/zju-vipa/Odyssey). | | [agentscope](/tools/agentscope-ai-agentscope.md) | [Odyssey](/tools/zju-vipa-odyssey.md) | | --- | --- | --- | | Tagline | Build and run agents you can see, understand and trust. | Odyssey: Empowering Minecraft Agents with Open-World Skills | | Stars | 27,752 | 396 | | Forks | 3,172 | 27 | | Open issues | 257 | 2 | | Language | Python | Python | | Adopt for | agentscope is a Python-based development tool focused on creating transparent and trustworthy AI agents. It supports the creation of both single and multi-agent systems incorporating large language models into its design | - | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | AI Agents, LLM Frameworks | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agentscope](/tools/agentscope-ai-agentscope.md) | [Odyssey](/tools/zju-vipa-odyssey.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Slowing (36%) | | Days since push | 1d | 262d | | Open issues (now) | 257 | 2 | | Security scan | No MCP manifest | No lockfile | | Full report | [trust report](/tools/agentscope-ai-agentscope/trust.md) | [trust report](/tools/zju-vipa-odyssey/trust.md) | ## Decision facts: agentscope - **Adopt for:** agentscope is a Python-based development tool focused on creating transparent and trustworthy AI agents. It supports the creation of both single and multi-agent systems incorporating large language models into its design ## Choose when ### Choose agentscope if… - License: agentscope is Apache-2.0, Odyssey is MIT. - Tags unique to agentscope: chatbot, multi-agent, multi-modal, react-agent. - - You need to develop AI agents where transparency and interpretability are critical. ### Choose Odyssey if… - License: Odyssey is MIT, agentscope is Apache-2.0. - Tags unique to Odyssey: embodied-agent, fine-tuning, large language model, minecraft. - Leaner open-issue backlog (2). ## When NOT to use agentscope - - If your project does not benefit from the transparency features offered by agentscope, and less emphasis is placed on interpretability and more on specialized machine learning tasks without a need理会 ## When NOT to use Odyssey - Last GitHub push was 263 days ago (slowing maintenance, Oct 22, 2025). Validate activity before betting a new project on Odyssey. - AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ## Common questions ### What is the difference between agentscope and Odyssey? agentscope: Build and run agents you can see, understand and trust.. Odyssey: Odyssey: Empowering Minecraft Agents with Open-World Skills. See the comparison table for live GitHub stats and shared categories. ### When should I choose agentscope over Odyssey? Choose agentscope over Odyssey when License: agentscope is Apache-2.0, Odyssey is MIT; Tags unique to agentscope: chatbot, multi-agent, multi-modal, react-agent; - You need to develop AI agents where transparency and interpretability are critical. ### When should I choose Odyssey over agentscope? Choose Odyssey over agentscope when License: Odyssey is MIT, agentscope is Apache-2.0; Tags unique to Odyssey: embodied-agent, fine-tuning, large language model, minecraft; Leaner open-issue backlog (2). ### When should I avoid agentscope? - If your project does not benefit from the transparency features offered by agentscope, and less emphasis is placed on interpretability and more on specialized machine learning tasks without a need理会 ### When should I avoid Odyssey? Last GitHub push was 263 days ago (slowing maintenance, Oct 22, 2025). Validate activity before betting a new project on Odyssey. AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ### Is agentscope or Odyssey more popular on GitHub? agentscope has more GitHub stars (27,752 vs 396). Stars measure visibility, not whether either tool fits your constraints. ### Are agentscope and Odyssey open source? Yes - both are open-source projects on GitHub (agentscope: Apache-2.0, Odyssey: MIT). ### Where can I find alternatives to agentscope or Odyssey? GraphCanon lists graph-backed alternatives at [agentscope alternatives](/tools/agentscope-ai-agentscope/alternatives) and [Odyssey alternatives](/tools/zju-vipa-odyssey/alternatives) ([agentscope markdown twin](/tools/agentscope-ai-agentscope/alternatives.md), [Odyssey markdown twin](/tools/zju-vipa-odyssey/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/agentscope-ai-agentscope-vs-zju-vipa-odyssey.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agentscope or Odyssey? agentscope: Very active. Odyssey: Slowing. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for agentscope and Odyssey? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agentscope trust report](/tools/agentscope-ai-agentscope/trust); [Odyssey trust report](/tools/zju-vipa-odyssey/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=agentscope-ai-agentscope`](/api/graphcanon/graph?tool=agentscope-ai-agentscope) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_