Human-Agent-Society

Human-Agent-Society/reef

Continual learning infra for self-improving agents

16 good first / help-wanted issues · Python · last activity Sep 2, 2026

61 stars 7 forks 61 watchers Python Apache License 2.0
View on GitHub Website
16 Open Issues Need Help Last updated: Sep 2, 2026

Open Issues Need Help

View All on GitHub
[Task] Bring uv.lock back in step with pyproject 11 days ago
good first issue area: ci type: task status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Feature] Add a native MLX training backend for Apple Silicon 13 days ago
enhancement help wanted area: ci area: training area: artifacts
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
`reef serve` with a dotted `reef.recipe` reference does not pass the yaml config to the recipe 17 days ago
bug good first issue area: service
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Reject non-finite values for declared float recipe settings 17 days ago
bug good first issue area: core area: training status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
`GET /reef/harness/install` 404s for a fresh scenario because the seed does not materialise into an initial artifact 18 days ago
bug good first issue area: service
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Send reef usage errors to stderr and exit 2 18 days ago
bug good first issue area: service status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Task] Remove the unreachable clause in the compaction-receipt conflict check 18 days ago
good first issue area: core type: task status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Reject an empty release_id when creating a scenario 18 days ago
bug good first issue area: service status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Reject a dotted serve override that traverses a non-section value 18 days ago
bug good first issue area: packaging area: service status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Parse the Bearer authentication scheme case-insensitively 20 days ago
bug good first issue area: service status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Validate deployment YAML structure and report clean config errors 20 days ago
bug good first issue area: packaging area: service status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Do not silently ignore stray reef serve arguments 20 days ago
bug good first issue area: service status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Reject duplicate service names before starting a stack 20 days ago
bug good first issue area: packaging area: service status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Reject non-finite report scores at the wire boundary 20 days ago
bug good first issue area: service status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Bug] Return HTTP 400 for non-object JSON request bodies 20 days ago
bug good first issue area: service status: ready
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python
[Feature] Report the last committed evolve step outcome in reef status 20 days ago
enhancement good first issue area: observability
Human-Agent-Society/reef
61

Continual learning infra for self-improving agents

Python