- Shenzhen, China
- longjin666.cn
Stars
Read-only multi-cloud MCP server with a provider-neutral query DSL
Local-disk, multi-tenant property graph database in Go with standalone or Share-Nothing Raft, tenant sharding, GraphQL/GQL, and S3 snapshot backups.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
JuiceFS is a distributed POSIX file system built on top of Redis and S3.
Web animation skill for Claude Code & Codex. 帮你做跟着滚动和鼠标动的网页动画。
DeepSeek Harness: Everything is a Plugin.
Make any agent harness multimodal-native.
Ansible is a radically simple IT automation platform that makes your applications and systems easier to deploy and maintain. Automate everything from code deployment to network configuration to clo…
A CNI meta-plugin for multi-homed pods in Kubernetes
Automated management of large-scale applications on Kubernetes (incubating project under CNCF)
Centralized agent control plane for governing runtime agent behavior at scale. Configurable, extensible, and production-ready.
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platforms such as MinIO and Ceph.
"AgentSpace: Human + Agents. One Team. One Workspace"
DeepSeek-V4-Flash on Ampere SM 8.6 via vLLM (pyref kernel replacements)
🎥 Make videos programmatically with React
Write HTML. Render video. Built for agents.
🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or…
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
The batteries-included agent harness.
Open vibecoding template with cloudbase.
Make humans and AI agents work as one team — open-source and self-hostable.
🌄 The Cloud Native Interactive Landscape filters and sorts hundreds of projects and products, and shows details including GitHub stars, funding, first and last commits, contributor counts and headq…
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed…