Tech News
Show HN: Whiteboard (YC W26) – An open-source IDE for thoughtful software design
Whiteboard is an open-source desktop IDE (built on CodeOSS) where humans and coding agents like Claude Code and Codex collaborate on a shared canvas.
Build a multi-account AI agent with AgentCore Gateway and MCP
Build a multi-account architecture that keeps each team's data in its own AWS account while giving AI agents a unified way to query across them.
Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war
Yesterday was Grok 4.7 ( pelicans ) and MiMo v2.6 Flash/Pro ( more pelicans ). Today Anthropic released Claude Opus 5.5, and around an hour later OpenAI released GPT-6 Sol and GPT-6 Luna.
vllm-project/vllm v0.30.0
v0.30.0 Highlights This release features 762 commits from 315 contributors (104 new)!
Parallel cut research time and cost in half with GPT‑6 Astra
GPT‑6 Astra allowed Parallel’s agents to research and synthesize labor-market data in half the time and at half the cost.
GitHub Repos
headroomlabs-ai/headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM.
# Python# agent# aibytedance/deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates.
# Python# agent# agenticHBAI-Ltd/Toonflow-app
Toonflow 是开源 AI 创作平台，融合无限画布、AI Agent 与可视化工作流，支持图像生成、视频生成、智能分镜及短剧创作。支持本地部署、自由接入模型，提供跨平台桌面端，并可通过 MCP 与插件扩展创作能力。Open-source AI creative platform with an infinite canvas, AI agents...
# TypeScript# ai# ai agentsResearch Papers
Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning
This paper proposes GRAFT, a method that builds a graph from multiple agent trajectories to estimate step-level advantages more accurately than GRPO. It uses Bellman iteration on the graph and a Graph GAE extension to reduce bias, claiming better performance on multi-turn...
SciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback
SciWalker automatically creates scientific coding problems by combining library functions into operator graphs, sampling workflows, and using execution feedback to fix generated problems and tests. Training an LLM on these problems improves its score on a scientific coding...
SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
A new preprint argues that long-horizon reasoning in LLMs fails due to exploration and compounding biases, and proposes SAGE, a framework that uses structural guidance to mitigate these biases.