Assistants & Domain Agents tools for opencode

role-playing approach for LLMs and auto-agents like BabyAGI & AutoGPT. github

跨设备的开源Agent工作台

LoopGPT is a modular auto-GPT framework with features such as a 'Plug N Play' API, GPT 3.5 compatibility, minimal prompt overhead, human-in-the-loop capability, and full state serialization, facilitating easy installation and usage through Python code, CLI, or Docker, with the ability to add custom tools and course correction, along with saving and loading agent state, requiring Python 3.8+ and an

Professional deep research report generation Skill — one command, ten minutes, broker-grade deep research / 深度调研报告生成 Skill — 一条命令，十分钟出券商级深度调研报告

V4 Flash 神模式 (opencode-go)：让 opencode-go 的 DeepSeek V4 Flash 从鬼模式切换到神模式的 dsh agent preset

DSH plugin — free OpenCode Zen models for DeepSeek Harness (DSH). Free LLM API, no API key needed. 在 DSH 中使用 OpenCode Zen 免费模型，无需 API key

Local-first CLI (MIT) that keeps one reviewed source of the MCP servers, tools, skills, and memory your AI coding agents share, synced into each tool's native config (Claude Code, Codex, Cursor, VS Code, OpenCode, and more) with a review gate before every write and a rollback receipt. No daemon, no lock-in

Git-native provenance for AI-written code: records which AI agent (Claude Code, Cursor, Copilot, Codex, Windsurf, OpenCode, Gemini) wrote which line, reconciles it against each commit, and signs every attribution with ed25519. Records live in your own git refs; no server. Rust, MIT/Apache-2.0

Open-source local memory and task queue for AI coding agents (Claude Code, Codex, opencode, Kimi): decisions survive context compaction, memory is anchored to code and follows it, everything stays in one SQLite file with no API key

Scans repos for coding-agent context bloat and ships a GitHub Action gate for Claude Code, Codex, Cursor, and OpenCode

Governance/control plane for AI coding agents. Validates risky actions, records findings, gates approvals, tracks budgets/providers, and creates proof bundles across Claude Code, Codex CLI, OpenCode, Cursor, and other hosts

Minimal repo-native project memory for AI coding agents. Installs AGENTS.md, project_context/, role Skills, and a validate-context gate so fresh Codex, Claude Code, Cursor, Gemini CLI, OpenCode, and similar sessions can recover project intent, boundaries, and validation paths

Reads your local coding-agent usage (Claude Code, Codex, Hermes, OpenCode) and shows which model gives you the same intelligence for less — scoring every model on the Artificial Analysis Intelligence Index and re-pricing your own token mix. 100% local, no account, MIT-licensed. Run with npx sidegrade; on npm

Tier-aware task router and skill-based workflow system for Claude Code that classifies tasks into Quick/Standard/Heavy/Vault/Learn tiers and routes them through the appropriate execution workflow with adaptive disambiguation