2962 posts
Local orchestration and routing for AI agents — gateway-first, agent-first, integration-first
Safe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes.
Autonomous yield for AI agents on Base. 80% liquid, 20% earning. No lockup. One SDK call.
Runtime guardrails for TypeScript AI agents. Prevents duplicate tool calls, enforces per-user cost budgets, and gates irreversible actions....
The operating manual for your codebase — written for AI agents. Shift-left intelligence layer that gives AI coding agents deep understanding...
Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.
Coding and research harness in pure Zig. Programmable in Lua
Desktop multi-agent orchestrator for the Claude Agent SDK. Command a hierarchy of AI agents — chiefs, specialists, advisors, workers — with...
Persistent memory MCP server for AI agents (MCP + REST)
浏览器仪表盘：在 PTY 下拉起你本机真实的 claude / codex / opencode / reasonix / zulu 命令行，组成一个协作蜂群（共享收件箱 + 黑板 + 队长调度）...
A curated list of 300+ tools, platforms, and resources for vibe coding and building software by talking to AI
Safe-by-default Oracle Database MCP server, in pure Rust — fail-closed SQL guard, engine-free, stdio + HTTP.
