Lite-Harness – Self-Hosted Cursor Agents (Use Claude Code/OpenCode)
One Dockerfile to rule Claude Code, OpenCode, and Codex with persistent sessions.
One normalized launcher for Codex, Claude Code, Gemini CLI, OpenCode, and Cursor Agent
Unified CLI for coding agents, but shell aliases or a simple script could do the same.
Developers experimenting with multiple local AI coding agents
aichat · llm
Instead of remembering different flags for Codex, Claude Code, Cursor Agent, OpenCode, and Antigravity CLI, I use one command with consistent options for agent, prompt, cwd, mode, model class, interactive/non-interactive and resume.
GitHub: https://github.com/dhruv-anand-aintech/agent-launch
You can use `agent-launch` or `agl` to launch (picks a random installed coding agent by default)
One Dockerfile to rule Claude Code, OpenCode, and Codex with persistent sessions.
tmux-native multiplex for AI agents with live traces and GOOD/BAD labels—niche but sharp for eval researchers.
Plumbs Cursor/Claude Code into Slack without rebuilding the agent logic.
IANA-registered .faf format with bi-sync, but only solves for power-users juggling 4+ tools.
Profile manager for AI agents — switch configs like dotfiles but for Claude and Cursor.
Ephemeral config staging for AI agents when each harness loads skills differently.