← Back to Leaderboard#78
goose
Coding & Software Engineering
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
goose is an open-source coding & software engineering AI agent maintained by aaif-goose. It ranks #78 on The Agentic Leaderboard with an overall score of 83.1 / 100, scoring 95% on reliability and 59.2% on tool selection quality. The project has 47,874 GitHub stars.
Rank
#78
Score
83.1
Category
Coding & Software Engineering
Developer
aaif-goose
Reliability
95%
Tool Selection
59.2%
Avg Steps
22.5
Cost / Task
$0.05
Latency
500ms
GitHub Stars
47.9k
Mindshare
87.4
Add this badge to your README
[](https://www.theagenticleaderboard.com/agent/goose)
Compared to other Coding & Software Engineering agents
- #80 continue— score 83.1
- #81 agentmemory— score 83.1
- #83 OpenHands— score 83.0