AI Infrastructure Engineer

Liang Li

I build the plumbing that makes AI agents actually work in production — agent frameworks, vector & knowledge-graph memory, MCP tool servers, and local-LLM integration. Go & Rust.

OPEN TO FREELANCE — agents · RAG · MCP Hire me → GitHub
Location
Chengdu, CN · Remote
Stack
Go · Rust · TS/React
Focus
Agents · RAG · MCP · Local LLM
Status
● Available for contract
01Agent Frameworks & Orchestration
harness-rs RUST
A Rust agent framework: ReAct loop, pluggable tools & skills, cross-session recall, a self-evolving learning loop, scheduler, sandbox, and an MCP client/server. Published on crates.io.
↗
agent-go GO
An AI Agent SDK for Go developers — teams, tasks, memory, MCP, tool calling.
↗
roma GO
Runtime Orchestrator for Multi-Agents.
↗
02Memory · Knowledge Graphs · RAG
cortexdb ★ flagship GO
A pure-Go, single-file AI memory & knowledge-graph library: vector + hybrid (BM25/FTS5) search, GraphRAG, and one-pass structured-data import. Zero external services, fully embedded.
↗
askdoc GO
Ask questions over your own documents (RAG).
↗
03MCP Servers — connect anything to an agent
mcp-swagger-server GO
Turn any Swagger / OpenAPI spec into ready-to-use MCP tools.
↗
mcp-websearch-server GO
Multi-engine web search with content extraction, exposed as MCP tools.
↗
mcp-sqlite-server GO
Expose a SQLite database to an agent over MCP. (+ mcp-snapshot-server)
↗
04Local-LLM & Infrastructure Tooling
ollama-go GO
A Go client library for Ollama.
↗
lmstudio-go GO
A Go client for LM Studio: chat, embeddings, tool calling, model management.
↗
gosible · dispatch GO
Infrastructure & multi-server automation in Go. (+ ollama-queue: a task queue for Ollama)
↗
05FAQ
What does Liang Li do?

Liang Li is an AI infrastructure engineer who builds agent frameworks, vector and knowledge-graph memory systems, MCP (Model Context Protocol) tool servers, and local-LLM integrations — primarily in Go and Rust.

Available for freelance / contract work?

Yes. He takes on contract work for AI agents, RAG and knowledge graphs, MCP integrations, and LLM-powered automation — taking an LLM from a demo to running unattended inside your real systems. Reach him at ll_faw@hotmail.com.

What are the main projects?

cortexdb (a pure-Go AI memory + knowledge-graph library with vector/hybrid search and GraphRAG), harness-rs (a Rust agent framework on crates.io), agent-go (a Go AI agent SDK), and a suite of MCP servers for Swagger/OpenAPI, web search, and SQLite.

I take an LLM from “demo” to running unattended inside your systems.

Emailll_faw@hotmail.com
GitHubgithub.com/liliang-cn