scale-agentex
Build, deploy, and scale agents at any level (L1–L5)
开源项目、精巧工具,还有让人眼前一亮的点子。
从 Hacker News 社区讨论中,找到你的下一份灵感。
Build, deploy, and scale agents at any level (L1–L5)
Retok: Token-efficiency analyzer for Claude Code and Codex CLI (zero deps)
DocETL: Declarative and Agentic Map-Reduce
Tkngate Zero-trust P2P ateway for LLM agents (open source, written in Go)
Mnemo AI – Local agentic assistant for any LLM that learns from its failures
Mwe-MCP – self-hosted memory for AI agents that knows who may know what
The Groundhog Trap – Multi-model consensus and AI output failover framework
Open-source skills that make any AI agent write native social posts
OpenMontage: an open-source agent that edits real footage into video
PrivAiTe: Self-hosted proxy that redacts PII from LLM calls, incl. tool-calls
Performant C/CUDA inference engine for Qwen 3.6 35B on RTX 5090 / Blackwell
Recursive AI Research Skill for Claude Code / OpenClaw / Codex
Chrome-agent: LLM-native browser automation tool written in Rust
AgentGrove – local workspace for AI coding agents in Git worktrees
Cicy-code – a local-first multi-agent coding workspace via npx
How do you audit what your autonomous agents did?
A reproducible harness for catching agent-eval cheating
ctx – Search the coding agent history already on your machine