OpenHands
PulseAugur coverage of OpenHands — every cluster mentioning OpenHands across labs, papers, and developer communities, ranked by signal.
- 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
6 day(s) with sentiment data
-
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 …
-
Ollama and FastAPI combine for enhanced local LLM API
Developers can create a more robust local LLM API by combining Ollama with FastAPI. Ollama simplifies the process of downloading and serving open-source models like Llama 3 and Mistral AI on a private server or local ma…
-
OpenHands open-source coding agent reaches 1.0 with production sandboxing
OpenHands, an open-source coding agent, has reached version 1.0, introducing production-ready sandboxing capabilities. This release aims to provide developers with a more secure and reliable environment for deploying AI…
-
Open-source tools offer alternative to costly AI subscriptions
A developer has outlined a suite of five open-source tools that can replace a costly monthly AI subscription, emphasizing control and cost savings. The proposed stack includes Ollama for local LLM inference, LiteLLM as …
-
AI coding tools add security with Universal Trust Adapter for MCP servers · 4 sources tracked
AliceLabs LLC has developed the Universal Trust Adapter (UTA), a system designed to add trust verification to MCP (Multi-Agent Communication Protocol) servers used by AI coding tools. The UTA, wrapped by the `@marketnow…
-
New framework reSolve enhances agent skill evolution and reproducibility
Researchers have developed reSolve, a new framework designed to improve the creation and reproducibility of agent skills. This system addresses the common issues of self-evolved skills underperforming human-curated ones…
-
Service health monitoring disconnect identified in OpenHands incident
A study has identified an incident where a service's health indicators remained green despite a conversation losing liveness, highlighting a potential disconnect in monitoring systems. This research also details a recov…
-
AI Physicist PhysMaster Outperforms Existing Agents on New Benchmark
Researchers have introduced PhysMaster, an autonomous AI physicist designed to tackle complex theoretical and computational physics research. To evaluate its capabilities, they developed PRL-Bench, a benchmark derived f…
-
New coding agent architecture proposes dumb runtime with smart subagent
A developer proposes a new architecture for coding agents where a simple 'main session' acts as a runtime, delegating complex tasks to a 'subagent'. This subagent would analyze the project, identify what's done, what's …
-
PerfAgent boosts LLM code optimization to expert levels
Researchers have developed PerfAgent, a novel system designed to enhance the code optimization capabilities of large language model (LLM) agents. Unlike previous agents that focused on correctness, PerfAgent uses profil…
-
Open-source AI ecosystem shows mixed performance, highlights key tools
The open-source AI ecosystem is experiencing fluctuations, with the OSAI Index showing varied daily performance. While some days saw significant increases, others experienced notable drops, indicating a dynamic and evol…
-
ContextForge tool combats LLM context rot with compression and reordering
Context rot, a phenomenon where LLMs lose accuracy in long conversations, is now measurable and can be mitigated. A new open-source tool called ContextForge acts as an intermediary, scoring, compressing, reordering, and…
-
NVIDIA releases Open-SWE-Traces dataset for AI software engineering training
NVIDIA has released Open-SWE-Traces, a dataset designed to train AI agents for software engineering tasks. A new tutorial from MarkTechPost demonstrates how to process this dataset for supervised fine-tuning. The tutori…
-
NVIDIA releases Nemotron 3 Ultra, a 550B parameter open-weights model
NVIDIA has released Nemotron 3 Ultra, a 550-billion-parameter open-weights model that sets a new benchmark for US-based releases. This hybrid Mamba-Transformer mixture-of-experts model features a 1M-token context window…
-
New framework reveals LLM code generation security flaws
A new framework called DualGauge has been developed to automatically benchmark the security and functionality of code generated by LLMs and coding agents. The accompanying DualGauge-Bench dataset includes 307 tasks with…
-
Paper defines 'agent harness' for AI coding assistants
A new paper published on arXiv proposes a formal definition for "agent harness," a term used in software engineering for systems that wrap language models to create coding agents. The authors trace the term's origins an…
-
Open-source AI coding agents reviewed for developer use
Several open-source AI coding agents are being reviewed for their capabilities in handling complex, multi-step tasks. These tools, including Tabby, Gemini CLI, OpenHands (formerly OpenDevin), and Plandex, offer self-hos…
-
AI Agents Fail Due to Data Issues, Not Model Limitations
AI agents often fail in production not due to the underlying model, but because of issues with the data they process. Common problems include undocumented data schemas, lack of normalization across different data source…