Open Issues Need Help
View All on GitHub Add Quick Search (Cmd+K / Ctrl+K) Command Palette to Web Dashboard about 2 months ago
enhancement good first issue
PicadoLabs/agent-bench PicadoLabs/agent-bench A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Open project →
1
A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Python
Add Go (Golang) Polyglot Benchmark Suite (feat-go-ratelimiter) about 2 months ago
enhancement good first issue
PicadoLabs/agent-bench PicadoLabs/agent-bench A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Open project →
1
A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Python
Add Leaderboard CSV / JSON Export button in Web Dashboard about 2 months ago
enhancement good first issue
PicadoLabs/agent-bench PicadoLabs/agent-bench A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Open project →
1
A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Python
enhancement good first issue
PicadoLabs/agent-bench PicadoLabs/agent-bench A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Open project →
1
A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Python
Wire agentbench ingest <pr_url> CLI command wrapper about 2 months ago
enhancement good first issue
PicadoLabs/agent-bench PicadoLabs/agent-bench A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Open project →
1
A local-first, provider-agnostic platform to benchmark, score, and diagnose autonomous AI coding agents on real-world software tasks.
Python