Omnara is an open-source managed agent platform - an Apache‑2.0, self-hostable alternative to Claude Managed Agents and OpenAI’s Agents API - that runs AI agents on any model and machine with built‑in tooling, secrets, permissions, and streaming. It offers an easy quickstart for Omnara Cloud and local Docker Compose self‑hosting, a CLI (npx omnara) for launching and chatting with agents, and a TypeScript SDK with examples showing createAgentConfig, createAgent, and openAgentEventStream. The repository includes documentation, examples, a frontend, and deployment assets; an instance can be configured with agent.yaml to pick model providers, machine pools, and launch agents that run commands, fetch files, and stream events back to clients.
The architecture centers on a REST API, a Postgres event log that records every agent step for durable state and recovery, stateless workers that assemble model context and run tools, and omnarad daemons on machines so agents can execute commands without inbound ports. It supports any compatible model provider (OpenAI, Anthropic, OpenRouter, Bedrock, LiteLLM, Ollama, self‑hosted), built‑in tools (shell, files, web fetch, human approvals), MCP/custom tools, reusable skills, memory stores, subagents, scheduled triggers, and sandboxes from multiple providers. Integrations include Slack, Discord, and GitHub, and the platform uses Redis, blob storage, and a memory filesystem to handle tooling outputs and attachments.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Claude now integrates with Google Docs, Sheets, and Slides through a new add-on and connectors in beta, allowing users to work directly within their files. It can read, edit, and suggest changes in documents, spreadsheets, and presentations without switching apps or tabs. (claude.com)
LLM agents were tested in a Pokémon Showdown 2v2 environment to evaluate their ability to coordinate and communicate during battles. Results showed that free communication improved win rates compared to restricted modes, demonstrating the potential for collaborative AI in strategic environments. (olivergrabner.com)
Huawei and DeepSeek have formed a partnership to combine Huawei's hardware and software with DeepSeek's workload expertise, enhancing AI model training and inference capabilities. By 2027 or 2028, DeepSeek is expected to rely mainly on Huawei's ecosystem to support a fully domestic Chinese AI infrastructure. (newsletter.semianalysis.com)
Linden is a low latency layer designed to verify AI outputs against schemas, data, and rules to ensure decision alignment with business requirements. Despite efforts to promote it, the developer has not gained any signups and questions whether the product serves a real purpose. (news.ycombinator.com)
Chopin is a real-time multiplayer environment designed to enhance team planning with AI agents, reducing cognitive load and improving decision-making. It emphasizes the importance of planning and review in software development, leveraging AI to streamline coding tasks and focus on strategic aspects. (githubnext.com)
OVHcloud, a French cloud computing company, aims to develop frontier AI models to become Europe's second large language model (LLM) provider by 2026. The company is investing in AI research to expand its presence in the AI industry. (reuters.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.