news

Oh My OpenAgent

Oh My OpenAgent (omo) is an agent-orchestration harness built on top of OpenCode; it coordinates multiple specialized agents to handle complex development work end-to-end with limited supervision. It was previously called oh-my-opencode.

Plannotator

Plannotator is an open-source review surface for AI coding agents; it lets you annotate the agent's plan before execution and review the resulting diff in a PR-style interface, then send structured feedback back to the agent with one click.

OpenChamber

OpenChamber is an open-source desktop and web interface built on top of OpenCode; it packages the agent harness into a multi-surface workspace for "engineering with agents".

Claude Code Agent View

Agent view, opened with `claude agents`, is one screen for dispatching and managing many background Claude Code sessions. Each row shows what a session is doing, what it needs, or what it produced — without scrolling through transcripts. Requires v2.1.139+; in research preview, so the UI and shortcu

RTK

RTK (Rust Token Killer) is an open source CLI proxy written in Rust that intercepts shell command output and compresses it before it reaches an AI coding agent's Context Window. It sits as a transparent hook between the agent and the underlying tools (git, cargo, npm, docker, kubectl, AWS CLI, etc.)

Software 3.0

Andrej Karpathy's term for software in which the runtime is a Large Language Model) and the program is a prompt (in natural language, structured prose, or markdown). The model interprets the prompt against the current input and emits behavior, optionally calling tools to interact with the world.

Agent Development Lifecycle (ADLC)

The Agent Development Lifecycle (ADLC) is the engineering discipline for building, evolving, and operating AI Agents in production. It is the agent-era counterpart to the Software Development Lifecycle (SDLC); the stages share names, but the failure modes, evaluation methods, and operational concern

LLM Tool Calling

Also called function calling. The pattern where a LLM) is given a list of available functions/tools (with names, descriptions, and parameter schemas), and the model decides when to invoke them and what arguments to pass. A host (an AI Agent Harness, an SDK, or the model provider's own platform) exec

Software Design Patterns for AI Skills and Agents

Software architecture principles transfer to AI skill and agent design with minimal translation. Skills behave like pure functions. Agents behave like microservices. The system forms a dependency graph governed by the same principles that make software maintainable.

Mistral SDK

The Mistral SDK is the official client library for Mistral AI's API platform, La Plateforme. Sits at the model SDK layer of AI SDKs, peer to Anthropic SDK and OpenAI SDK. Officially supported in Python (`mistralai`) and TypeScript / JavaScript (`@mistralai/mistralai`), with a Go and TypeScript imple

2026-05-14 Obsidian Sync Passes Cure53 and Trail of Bits Audits

The Obsidian team just published the results of two independent security audits of Obsidian Sync; one by Cure53 (Berlin, October 2024) and one by Trail of Bits (New York, December 2025). Both cover the Sync API, server, and cryptography. All findings have been addressed via remediations validated by

Hermes Agent

Hermes Agent is Nous Research's open-source, model-agnostic agent harness; distinct from the Hermes LLM line that shares the name. Where Hermes (the model) is a fine-tuned base, Hermes Agent is the surrounding scaffolding that turns any LLM into a long-running personal assistant with skills, memory,