Skip to content
#

Agent Harness

Star

Agent harnesses are the runtime scaffolding around AI agents. They usually combine context delivery, tool interfaces, planning state, memory, sandboxes, permissions, evaluation, and observability so agents can complete longer tasks reliably. Agent harnesses are especially common in coding agents, research agents, and multi-agent workflows where repeatability, safety, and traceability matter.

Here are 6 public repositories matching this topic...

Language: Kotlin
Filter by language
All 1,388 Python 521 TypeScript 332 JavaScript 150 Rust 82 Shell 52 HTML 51 Go 48 Java 10 C# 7 Kotlin 6

risa-labs-inc / BossConsole

Star 812

Open-source, multi-platform harness for AI agents - a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Codex, Gemini or OpenCode with a real browser, terminal, editor, secrets & 100+ MCP tools. Built for enterprises, science & research.

desktop-app open-source browser terminal jvm mcp opencode multithreading gemini rbac hot-reload codex ai-agents kotlin-multiplatform compose-multiplatform llm model-context-protocol claude-code agent-harness
  • Updated Oct 1, 2026
  • Kotlin
Followers
190 followers
Website
github.com/topics/agent-harness

Related topics

agent-framework ai-agents autonomous-agents coding-agents mcp