Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
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 }}
amd
/
gaia
Public
Notifications
You must be signed in to change notification settings
Fork
174
Star
1.6k
Code
Issues
1k
Pull requests
24
Actions
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Security and quality
Insights
All pull requests
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
24
(24)
Closed
2,066
(2,066)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
More items
Comfortable display density
Compact display density
fix(ci): clear the two smoke failures still red on every PR
tests
#4580
·
kovtcharov
opened
Oct 2, 2026
Contributor
·
2 of 4 tasks
·
·
1
feat(tools): a Literal-typed tool argument is sent as a JSON-schema enum
agents
tests
#4575
·
kovtcharov
opened
Oct 2, 2026
Contributor
·
2 of 3 tasks
·
·
1
fix(chat): only teach image generation when the session has it
tests
#4574
·
kovtcharov
opened
Oct 2, 2026
Contributor
·
1 of 3 tasks
·
·
1
perf(chat): name indexed documents per turn, not in the system prompt
tests
#4571
·
kovtcharov
opened
Oct 2, 2026
Contributor
·
2 of 4 tasks
·
·
1
fix(eval): a SWE-bench run never keeps the gold patch on disk
documentation
eval
performance
tests
#4559
·
kovtcharov
opened
Oct 1, 2026
Contributor
·
2 tasks done
·
·
1
fix(agent): a tool call cut off at the output cap is retried with shorter arguments
agents
tests
#4556
·
kovtcharov
opened
Oct 1, 2026
Contributor
·
2 of 4 tasks
·
·
1
fix(gaia): offer the flagship every tool on every turn, as the Agent UI does
documentation
sidecar
#4554
·
kovtcharov
opened
Oct 1, 2026
Contributor
·
2 of 3 tasks
·
·
2
fix(webui): the chat header names the session's model
documentation
tests
#4550
·
kovtcharov
opened
Oct 1, 2026
Contributor
·
3 tasks done
·
·
1
fix(agent): tell the flagship its working directory outside a project
agents
tests
#4546
·
kovtcharov
opened
Oct 1, 2026
Contributor
·
1 of 2 tasks
·
·
1
perf(llm): local chat model keeps the conversation cached across side requests
agents
llm
performance
tests
#4543
·
kovtcharov
opened
Oct 1, 2026
Contributor
·
3 tasks done
·
·
4
fix(agent): GAIA's own checks no longer trip the after-answer scope guard
agents
eval
performance
tests
#4540
·
kovtcharov
opened
Oct 1, 2026
Contributor
·
3 tasks done
·
·
1
feat(agent): the project map says which dependencies are missing and where the agent may work
agents
tests
#4537
·
kovtcharov
opened
Oct 1, 2026
Contributor
·
2 tasks
·
·
1
fix(connectors): derive the flagship's mail scopes for --grant-agent
#4533
·
github-actions[bot]
opened
Sep 30, 2026
Bot
·
5 tasks
·
·
1
fix(agent): check answers against what the turn's tools actually did
agents
documentation
tests
#4532
·
kovtcharov
opened
Sep 30, 2026
Contributor
·
3 tasks
·
·
1
docs(email): the mail guide describes one agent — the flagship
agent::email
documentation
tests
#4530
·
itomek
opened
Sep 30, 2026
Collaborator
·
1 of 7 tasks
·
·
1
4
fix(cli): gaia chat runs the flagship GaiaAgent
cli
documentation
tests
#4520
·
kovtcharov
opened
Sep 30, 2026
Contributor
·
2 of 3 tasks
·
·
1
feat(webui): one simple chat app for the GAIA agent, with first-run setup
agent::email
cli
documentation
electron
llm
performance
security
tests
website
#4509
·
kovtcharov
opened
Sep 30, 2026
Contributor
·
12 of 14 tasks
·
·
1
feat(agent): plain-English verification note, shown only when work isn't confirmed
agents
documentation
eval
performance
tests
tui
#4508
·
kovtcharov
opened
Sep 30, 2026
Contributor
·
3 of 4 tasks
·
·
1
fix(agent): look at named files before answering about them
agents
tests
#4501
·
kovtcharov
opened
Sep 29, 2026
Contributor
·
2 of 3 tasks
·
·
1
feat(models): make Qwen3 30B A3B the local default; Qwen3.8 Flash becomes a manual option
agents
cli
devops
documentation
llm
performance
tests
tui
#4479
·
kovtcharov-amd
opened
Sep 29, 2026
Collaborator
·
4 of 5 tasks
·
·
2
test(eval): validate every flagship capability at four tiers
cli
devops
documentation
eval
performance
tests
#4472
·
kovtcharov
opened
Sep 29, 2026
Contributor
·
4 of 5 tasks
·
·
1
fix(tui): proportionate permission prompts, Shift+Tab modes, timeouts as timeouts
agents
documentation
tests
tui
#4461
·
kovtcharov
opened
Sep 29, 2026
Contributor
·
5 tasks
·
·
1
3
fix(agent): a declined action is not run another way
agents
devops
documentation
eval
mcp
performance
tests
#4460
·
kovtcharov
opened
Sep 29, 2026
Contributor
·
4 of 8 tasks
·
·
1
4
feat(eval): give the flagship agent a measured scorecard and a release gate
devops
documentation
eval
performance
ready_for_ci
sidecar
tests
#4056
·
itomek
opened
Sep 21, 2026
Collaborator
·
5 of 8 tasks
·
·
6
You can’t perform that action at this time.