OpenHands
PulseAugur coverage of OpenHands — every cluster mentioning OpenHands across labs, papers, and developer communities, ranked by signal.
- 2026-10-24 product_launch OpenHands launched version 1.33.0 with new features and bug fixes. source
- 2026-10-12 product_launch OpenHands released version 1.27.0 with new features for mock-LLM testing and browser recording. source
- 2026-10-06 product_launch OpenHands released version 1.25.0 with updates to its back navigation control. source
- 2026-09-17 product_launch OpenHands released version 1.19.0 with new features including GPT-6 Astra model support. source
- 2026-09-12 product_launch OpenHands released version 1.18.0 with new features including full-size image viewing and enhanced automation controls. source
- 2026-09-08 product_launch The open-source coding agent OpenHands has been released in version 1.0, featuring production-ready sandboxing. source
10 day(s) with sentiment data
-
Chinese AI 'Tu Long Feng' Tops Global Security Benchmark, Beats OpenAI and Google
A Chinese AI security system named Tu Long Feng, developed by 360 Security, has achieved a record-breaking 99.4% success rate on the CyberGym leaderboard, a benchmark for AI security capabilities. This achievement surpa…
-
AI agent harnesses enforce quality via tool calls, reducing prompt reliance
Several open-source AI agent harnesses, including OpenHands SDK, OpenCode, Hermes Agent, DeepSeek Harness, and Strands, offer improved quality control by enforcing rules at the tool-call level rather than relying solely…
-
OpenHands releases developer QuickStart guide for LLM CLI
OpenHands has released a QuickStart guide for developers, detailing how to install its command-line interface (CLI). The guide covers configuring LLM API keys, understanding core command-line flags, and exploring safety…
-
Headroom tool compresses Claude Code token usage for cost savings
Headroom is an open-source tool designed to reduce the token costs associated with using AI models like Claude Code. It functions by compressing the input data sent to the model, such as logs and tool outputs, before it…
-
New AI method SWE-Ladder enhances software repair capabilities
Researchers have developed SWE-Ladder, a novel approach to training AI agents for software engineering tasks. This method utilizes progressive privileged self-distillation, breaking down the repair process into distinct…
-
OpenHands v1.33.0 Launches with New Verification Options
OpenHands has released version 1.33.0, introducing new options like --mars-web and --lock-to-cloud for verification. This update also ensures the DigitalOcean web build maintains sign-in status across restarts and impro…
-
New PAUSE framework improves coding agent steering; PaletteGet tool aids accessibility
A new framework called PAUSE has been developed to steer coding agents more effectively by intervening before their first source-code edit. This method, which requires no learned monitor or extra model calls, uses a sep…
-
New method enables seamless transfer of coding agent work
A new method called agent-handoff allows the work of one coding agent to be transferred to another without losing progress. This technique converts session logs from agents like OpenCode or Codex into tasks that other a…
-
Vibe Kanban users seek alternatives amid service changes
Users are seeking alternatives to Vibe Kanban following changes to its hosted services. When evaluating new tools, it's recommended to consider workflow aspects such as local coding-agent execution, parallel task manage…
-
OpenHands v1.28.0 adds Indonesian language support and bug fixes
OpenHands has released version 1.28.0, which includes Indonesian language support and fixes for known bugs. This update also introduces a repeatable fix proof for verify-openhands and allows agents to request secrets vi…
-
AI agent memory audits reveal critical data omissions, impacting trace replayability
An audit of stored memory items in public AI agent traces revealed significant issues with how their state is recorded and analyzed. The author found that most traces only provide the conversation transcript, omitting c…
-
OpenHands v1.27.0 enhances mock-LLM testing and browser recording
OpenHands has released version 1.27.0, introducing enhanced mock-LLM capabilities for testing end-to-end behaviors and improving browser video recording functionality. This update also integrates OpenCode and Pi as buil…
-
OpenHands releases v1.25.0 with navigation updates
OpenHands has released version 1.25.0, which includes updates to its back navigation control on settings sub-pages. This release, dated October 6, 2026, has garnered significant attention with over 90,000 stars.
-
OpenHands v1.25.0 adds bulk LLM profile creation; Fluxer adds custom themes
OpenHands has released version 1.25.0, which introduces the capability for bulk creation of LLM profiles within its settings. Additionally, Fluxer's fluxer-app-proxy-self-hosted has been updated to version 2026.1006.162…
-
New benchmarks evaluate LLMs' code generation, clarification, and retrieval capabilities
Three new research papers introduce novel benchmarks and methods for evaluating Large Language Models (LLMs) in code generation tasks. ClarifyCodeBench focuses on an LLM's ability to clarify ambiguous requirements, find…
-
AI for AI: Labs Automate Model Development, Accelerating AGI Race
The concept of "AI for AI" is emerging as a core focus in the development of next-generation large language models. This approach leverages AI's capabilities to automate and accelerate the research and development proce…
-
New research explores optimizing agent harnesses for improved AI performance · 9 sources tracked
Multiple research papers explore the optimization and evolution of agent harnesses, which are crucial components that dictate how language models interact with their environments. Studies introduce novel frameworks like…
-
OpenHands v1.19.0 adds GPT-6 Astra model support and MCP server scoping
OpenHands has released version 1.19.0, introducing several new features. This update allows for the scoping of agent profiles to specific MCP servers. Additionally, it incorporates support for the GPT-6 Astra model and …
-
Self-hosted AI dev team AICOM automates product deployment
The developer has created a self-hosted AI development team, named AICOM, as an alternative to hosted AI app builders. Unlike simpler chat-to-code tools, AICOM utilizes thirteen specialized agents, including analysts, d…
-
OpenHands v1.18.0 adds image viewing and automation control features
OpenHands has released version 1.18.0, introducing several new features. Users can now click on image attachments to view them in full size. Additionally, only the creator of an automation can re-enable it, and editing …