agent-orchestration-kernel: execution kernel for AI systems trends on GitHub
An execution kernel for AI systems featuring agent orchestration, capability routing, memory coordination, policy enforcement, workflow execution, and runtime management. Now trending on GitHub.
Google open-sources Harness² for self-improving AI agents
Google open-sourced Harness², a way to improve AI agents without touching the model. The agent rewrites its own harness while the model weights stay frozen.
Aetherra: self-evolving AI-native language platform trends on GitHub
Aetherra is a self-evolving, AI-native language and platform for intelligent agents and autonomous software. Now trending on GitHub.
Amp Puts AI Agents to Work Beyond Code with OpenAI Models
Amp pushes the frontier of what agents can do using GPT-6 Astra, Ultrafast, GPT-Live-1, and Sign in with ChatGPT.
AonicClub applies agents to physical goods sourcing
The post says AI rebuilt coding and legal drafting, yet supplement and grocery prices have not fallen. AonicClub applies agents to physical goods, handling sourcing and operations work.
OpenAI and Ironclad train agents for contracting workflows
OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows, advancing computer use for professional enterprise legal work.
Yetone adds session viewing for more Agents
Yetone says session viewing and management now supports more Agents, without naming a product, version, or detailed capability limits.
Developer Buzz: Anticipating Google's Antigravity Comeback
chunxiangai jokes about a major information gap, eagerly calling for Google to bring back Antigravity, reflecting community hype around Google's agentic product line.
Stripe: top AI firms grow 175%
Stripe's AI CRO says top AI firms grew 175%, about 48% of revenue is outside the home market, and agents may soon read more Stripe docs than humans.
Anthropic wet lab's first discovery by 950 Claude agents
Per The Verge, Anthropic's new wet lab made its first discovery: nearly 950 Claude agents worked independently for 21 hours, consuming 210 million tokens, to find a new enzyme.