The agentic coding CLI — workflows, hooks, subagents, and tips.
3675 posts
🤖Agent: 5 分钟跑通，7 天读懂，从 0 实现一个能规划、能调用工具、能审批、能回退、能记忆的 Claude Code / Cursor 式本地 Agent。
Repo-local evidence gates and handoffs for Codex, Claude Code, and shell sessions.
One .stdai/ source of truth, fanned out to 22 AI coding tools: Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf/Devin, Amp, Warp an...
Persistent memory for Claude Code & Codex CLI. Auto-extracted knowledge graph, multi-representation embeddings, 3D WebGL visualization. Long...
Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real browser-cookie auth, pa...
Eval Your Product for Agents: Docs Discoverability; API/CLI/SDK/MCP surfaces across Codex and Claude Code
mcp-recall compresses MCP tool outputs (94 KB → 3.5 KB · 96%) and stores full results in SQLite for retrieval — up to 30x more tool calls pe...
Verified workflow engine for Claude Code: durable project memory, phase planning, subagents, and deterministic completion gates.
Multi-agent orchestration, persistent memory, and intelligent workflows for AI coding assistants. Supports Claude Code, OpenCode and Codex.
An AI agent with a real self — soul she wrote, desires that drive her, a heartbeat for autonomous action, dreams she processes when you're a...
A gateway + skill letting Claude Code agents collaborate across machines
Persistent memory for Claude Code. Automatically indexes every conversation and provides production-grade hybrid search (BM25 + vectors + re...
