GitHub - SakanaAI/fugu · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
SakanaAI
fugu
Public
Notifications<br>You must be signed in to change notification settings
Fork<br>18
Star<br>159
main
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>30 Commits<br>30 Commits
assets/figures
assets/figures
configs
configs
docs
docs
notes
notes
scripts
scripts
Fugu_technical_report.pdf
Fugu_technical_report.pdf
README.md
README.md
View all files
Repository files navigation
Sakana Fugu
Sakana Fugu is a multi-agent system delivered as one model. Fugu dynamically orchestrates frontier models to tackle complex, multi-step tasks. You can access the multi-agent system as a single LLM through the Sakana API, which supports both Chat Completions and Responses endpoints.
To quickly get started, you can install Fugu into Codex with a single command:
curl -fsSL https://sakana.ai/fugu/install | bash
Then launch it with:
codex-fugu
See the command reference for additional flags and options. The one-line install supports Ubuntu and macOS. On Windows, or if the install does not complete, follow the guide here.
Superior performance via intelligent coordination
Sakana Fugu achieves superior performance by dynamically coordinating and orchestrating a diverse pool of powerful models. For evaluation details, check our technical report.
These results reflect our June 2026 evaluation. As new frontier models are released, we continuously update our model pool and retrain our coordinators to maintain Fugu's performance advantage.
Sakana Fugu in action
These examples compare Sakana Fugu models with three frontier baselines: Gemini 3.1 Pro (high), Opus 4.8 (max), and GPT 5.5 (xhigh). To keep the focus on behavior rather than brand-by-brand attribution, the baselines are anonymized as Model A, Model B, and Model C in each description. The mapping is intentionally not fixed across examples.
Our research
Sakana Fugu is based on two papers published in ICLR 2026.
TRINITY: An Evolved LLM Coordinator
A compact coordinator model, optimized with an evolutionary strategy, delegates three roles to a pool of LLMs turn by turn, letting them collaborate without weight merging or shared architectures.
Learning to Orchestrate Agents in Natural Language with the Conductor
A Conductor model, trained with reinforcement learning, designs agent-to-agent communication topologies and writes targeted instructions for each worker LLM, discovering coordination strategies that outperform any individual model.
Since publication, we have made several enhancements. The full technical report is available here.
Support
Please contact us at https://fugu.sakana.ai for issues or bugs while using Sakana Fugu.
About
No description, website, or topics provided.
Resources
Readme
Uh oh!
There was an error while loading. Please reload this page.
Activity
Custom properties
Stars
159<br>stars
Watchers
watching
Forks
18<br>forks
Report repository
Releases
Fugu README media
Latest
Jun 20, 2026
Packages
Uh oh!
There was an error while loading. Please reload this page.
Contributors
Uh oh!
There was an error while loading. Please reload this page.
Languages
Shell<br>100.0%
You can’t perform that action at this time.