oh-my-openagent: TypeScript Agent Harness (formerly oh-my-opencode)
oh-my-openagent (omo) is a TypeScript-based agent harness project on GitHub, previously known as oh-my-opencode. The repository has accumulated 58,729 stars with 180 new stars today, indicating significant community traction. The rename from 'opencode' to 'openagent' suggests a broadening scope beyond code-focused tasks toward general agent capabilities.
Related guides (1)
Related events (8)
opencode: Open Source Coding Agent (TypeScript) Trending on GitHub
The repository anomalyco/opencode is a TypeScript-based open-source coding agent that has accumulated 164,043 stars on GitHub, with 514 new stars added today. It represents a community-driven alternative in the coding agent space. The high star count suggests significant developer adoption or interest in open-weight/open-source coding agent tooling.
stablyai/orca: Agent Development Environment for parallel coding agent fleets
Orca is an open-source Agent Development Environment (ADE) built in TypeScript that enables running fleets of parallel coding agents using a user's own model subscriptions. It targets desktop and mobile platforms. The project has accumulated 5,493 GitHub stars with 117 added today, indicating meaningful community traction.
oh-my-pi: Terminal AI Coding Agent with Hash-Anchored Edits and LSP Integration
oh-my-pi is an open-source TypeScript AI coding agent designed for terminal use, featuring hash-anchored file edits, an optimized tool harness, LSP integration, Python execution, browser access, and subagent support. The project has accumulated 5,362 GitHub stars with 237 added today, indicating rapid community traction. It represents a self-contained agentic coding environment targeting developer workflows in the terminal.
agent-teams-ai: multi-agent orchestration framework with kanban-style oversight
A TypeScript open-source project on GitHub implements a multi-agent system where autonomous agents handle tasks, communicate with each other, and review each other's work, while the user supervises via a kanban board. The framework supports 200+ models across 75+ LLM providers including Codex, Claude, and OpenCode. It has accumulated 1,189 stars with 56 added today, suggesting growing community interest.
OpenMontage: open-source agentic video production system with 52 tools and 500+ agent skills
OpenMontage is a newly trending open-source Python project claiming to be the first agentic video production system, offering 12 pipelines, 52 tools, and 500+ agent skills. It is designed to extend AI coding assistants into full video production workflows. The project has accumulated 5,231 GitHub stars with 71 added today, indicating notable community traction.
Building the Open Agent Ecosystem Together: Introducing OpenEnv
Hugging Face has announced OpenEnv, an initiative aimed at building an open ecosystem for AI agents. The project appears to focus on standardizing and sharing environments for agent training and evaluation. As a tier-2 source commentary piece, it signals Hugging Face's continued investment in the agent tooling space and open-source agent infrastructure.
Multica: Open-Source Managed Agents Platform for Coding Agents
Multica is an open-source TypeScript platform designed to turn coding agents into collaborative teammates, supporting task assignment, progress tracking, and skill compounding. The project has accumulated 31,871 GitHub stars with 429 added today, indicating significant community traction. It positions itself as a managed agents infrastructure layer for developer workflows.
Code as Agent Harness: A Survey of Code as Operational Substrate for Agentic AI Systems
This survey paper introduces the concept of 'code as agent harness,' framing code not merely as output but as the operational infrastructure for LLM-based agents—covering reasoning, action, environment modeling, and execution-based verification. The authors organize the analysis across three layers: harness interface, harness mechanisms (planning, memory, tool use, feedback control), and scaling to multi-agent systems. Applications span coding assistants, GUI/OS automation, embodied agents, scientific discovery, and enterprise workflows. Open challenges include evaluation beyond task success, verification under incomplete feedback, and human oversight for safety-critical actions.