Toolbox/Agent SDKs & frameworks/Human-Agent-Society/reef

Human-Agent-Society/reef

Continual learning infra for self-improving agents

View on GitHub →
PythonApache-2.0agent-infrastructureai-agentscontinual-learninginferencellm
Stars
1.2k
Δ 7d
Δ 30d
Age
2 wk
Last push
33m ago
1.2k1.2k1.2k1.2k1.2kSep 13
90-day star history

Where this sits in the catalog

Most-wanted open issues

Ranked by 👍 reactions. 54 open issues total, checked 2026-09-13.

Issue👍CommentsOpened
[Community] Reef Roadmap

roadmap, status: keep-open

302 wk
103 d
001 wk
[Example] Run CORAL multi-agent test-time training through Reef and Slime

area: examples, area: harness, area: training, type: example, KIV

002 wk
[RFC] Prioritized scheduling across serving, scoring, and training

enhancement, area: service, area: training, performance, RFC, KIV

002 wk

Alternatives in Agent SDKs & frameworks

DeepSeek Harness: Everything is a Plugin.

222.0k
+8,4387d
TypeScript
1 mo

The agent engineering platform.

146.2k
+4597d
Python
3 yrs

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory a…

46.9k
+1527d
Python
4 yrs

Build, run, and manage agent platforms.

42.1k
+827d
Python
4 yrs

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI P…

37.3k
+1227d
TypeScript
3 yrs

Build and run agents you can see, understand and trust.

31.5k
+6787d
Python
2 yrs