Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects, and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Developer articles
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
Human-Agent-Society
reef
Repository navigation
Code
Issues
126
(126)
Pull requests
33
(33)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
48
(48)
Milestones
0
(0)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
33
(33)
Closed
1,008
(1,008)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
fix(deploy): stop the services when reef serve hangs up
area: docs
area: service
area: training
#1461
·
Plastic-time
opened
Nov 16, 2026
·
9 tasks done
·
·
build(deps-dev): bump the python-minor-and-patch group with 3 updates
area: packaging
dependencies
#1459
·
dependabot[bot]
opened
Nov 16, 2026
Bot
·
·
fix: allow LoRA startup on SGLang 0.5.21
area: training
#1375
·
dannyward630
opened
Nov 12, 2026
·
8 of 9 tasks
·
·
1
7
docs(harness): add custom-agent guide and LangGraph example
area: docs
#1344
·
jane-jhu
opened
Nov 11, 2026
Contributor
·
8 of 9 tasks
·
·
feat(routing): add bounded shadow execution for OPD
area: core
area: docs
area: service
#1309
·
RickWayne1125
opened
Nov 9, 2026
Contributor
·
8 of 9 tasks
·
·
test(scenario): check control and the samples service as separate dis…
type: tests
#1306
·
Sounakray2003
opened
Nov 9, 2026
·
9 tasks
·
·
feat(reasoning-bank): add memory retrieval and periodic ablation
area: docs
area: harness
#1279
·
jane-jhu
opened
Nov 8, 2026
Contributor
·
9 tasks done
·
·
1
feat: train SPADE's Environment Designer on its own replies on Slime (RFC #1261)
area: core
area: docs
area: harness
area: service
area: training
#1262
·
Benjamin-eecs
opened
Nov 8, 2026
Member
·
8 of 9 tasks
·
·
1
feat!: generate AutoEnvScaling tasks from seed tasks, and train them again in a reviewed training pool
area: core
area: docs
#1214
·
Benjamin-eecs
opened
Nov 6, 2026
Member
·
9 tasks done
·
·
12
9
fix(recipe)!: refuse image content for weight-training recipes that do not support images
area: core
area: docs
area: service
area: training
#1191
·
augustuszzq
opened
Nov 5, 2026
Contributor
·
8 of 9 tasks
·
·
[Docker] Add vLLM to the Reef image as the second serving engine
area: docs
area: harness
area: packaging
dependencies
#1153
·
ruizhang0101
opened
Nov 4, 2026
Collaborator
·
9 tasks done
·
·
1
fix: skip policy reports without trainable tokens
area: harness
#1126
·
mikemikimike
opened
Nov 2, 2026
·
·
1
1
feat(recipes): skill_library, procedural skills kept only after a replay of their task
area: docs
area: examples
area: packaging
dependencies
#1096
·
Xuan-1998
opened
Nov 2, 2026
Collaborator
·
·
2
chore(harness): list the open harness tasks
area: docs
#1081
·
quao627
opened
Nov 2, 2026
Contributor
·
1 of 16 tasks
·
·
2
refactor(ace): split the step loop, the model roles and the playbook into modules, and document the online loop
area: docs
#1076
·
quao627
opened
Nov 2, 2026
Contributor
·
9 tasks done
·
·
1
feat: in manual mode, a client requests each task-generation round and names its source sessions (RFC #1065)
area: core
area: docs
area: service
area: training
#1066
·
BobbyZhouZijian
opened
Nov 1, 2026
Contributor
·
8 of 9 tasks
·
·
refactor(evaluation)!: an evaluation task is a record with an id, an instruction and an answer
area: docs
area: examples
area: harness
area: service
area: training
#1027
·
quao627
opened
Oct 30, 2026
Contributor
·
8 of 9 tasks
·
·
fix(dispatcher): say which scenario a report must use when its reference is not found
area: training
#976
·
ChokepointPT
opened
Oct 28, 2026
·
9 tasks done
·
·
1
feat(train): install YaRN from the checkpoint config in Reef's Megatron provider
area: docs
area: training
#930
·
MikeZheng777
opened
Oct 26, 2026
Contributor
·
8 of 9 tasks
·
·
feat(guidance-ttt): add four CPU-only FrontierCS 2 tasks
area: docs
area: examples
area: harness
#923
·
wenhaochai
opened
Oct 25, 2026
Collaborator
·
9 tasks done
·
·
6
Add Retail L1 SAO continual training and checkpoint resume
area: docs
area: examples
area: harness
area: training
dependencies
#911
·
Chonghe-Jiang
opened
Oct 24, 2026
Collaborator
·
9 tasks done
·
·
1
feat(opd): normalize the sampled reverse-KL advantages over the training job
area: docs
area: examples
area: training
#830
·
BobbyZhouZijian
opened
Oct 16, 2026
Contributor
·
9 tasks done
·
·
Feat/multi tenant scheduler dev
area: core
area: docs
area: harness
area: service
area: training
#822
·
Martin-HZK
opened
Oct 15, 2026
·
·
1
feat(observability): report model-call usage for each scenario
area: core
area: docs
area: harness
area: service
area: training
#816
·
BobbyZhouZijian
opened
Oct 15, 2026
Contributor
·
9 tasks done
·
·
[Docker] Add the vLLM training image (Slime on torch 2.13 plus vLLM)
area: ci
area: docs
area: packaging
dependencies
#774
·
ruizhang0101
opened
Oct 13, 2026
Collaborator
·
9 tasks done
·
·
3
Previous
1
2
Next
You can’t perform that action at this time.