This manual explains Amp, an agentic coding tool by Sourcegraph for VS Code and CLI. It details principles like unconstrained tokens and automatic model selection, plus prompting guidelines for effective use.
Highlights
Amp integrates with VS Code and forks, supporting multiplayer collaboration.
It uses unconstrained tokens and auto-selects best models like Claude Sonnet 4.
Users should break tasks into sub-tasks and use AGENT.md for guidance.
Prompts should be explicit and leverage git commands for context.
The tool prioritizes raw model power over subscription cost matching.
API for Cursor - Cursor Composer in Any Coding Agent
Use Cursor’s models with any harness. Run Composer through a local OpenAI-compatible API for OpenCode, Codex, VS Code, Cline, Kilo Code, pi, and your ...
opencode.ai
opencode
The AI coding agent built for the terminal.
github.com
GitHub - omnigent-ai/omnigent: A meta-harness for all your AI agents. Omnigent provides a common layer over Claude Code, Codex, Pi, and the agents you write yourself: swap or combine harnesses without rewriting, keep them in check with policies and sandboxing, and collaborate in real time on the same live session, from any device.
A meta-harness for all your AI agents. Omnigent provides a common layer over Claude Code, Codex, Pi, and the agents you write yourself: swap or combin...