Pipe – a semantic pipeline runtime with built-in MCP (Go)

harrymachura1 pts0 comments

Pipe — The runtime for AI-native infrastructure

SPR v0.9.2 · Semantic Pipeline Runtime

MCP-native runtime for<br>AI infrastructure

The first language with built-in MCP — server and client. Connect to 100+ MCP servers, expose your own tools, and run AI pipelines. Single ~7 MB binary, zero dependencies.

43AI Builtins

300+Tests

193Total Builtins

4Providers

23Modules

▶ Try in Browser<br>⬇ Download for Linux<br>Read the Docs →

v0.9.2 · ~7 MB single binary · Linux · macOS · Windows · Raspberry Pi

v0.9.2 · ~7 MB einzelne Binary · Linux · macOS · Windows · Raspberry Pi

curl -fsSL https://pipe-lang.com/install.sh | bash

pipe — demo

A real pipeline: classify → summarize → translate → save. Run it yourself below ↓

Eine echte Pipeline: klassifizieren → zusammenfassen → übersetzen → speichern. Probier sie unten selbst aus ↓

Try Pipe in your browser

Probier Pipe im Browser

No install. No signup. Just type Pipe code and run.

Keine Installation. Keine Anmeldung. Einfach tippen und ausführen.

pipe playground

Graph<br>▶ Run

"hello world"<br>> upper<br>> print

Loading WASM...

API Key (optional)<br>DeepSeek<br>OpenAI<br>Anthropic

pipeline graph

Running AI in production is harder than it should be

KI in Produktion ist schwieriger als nötig

🔒

Security

Sicherheit

LLMs with file access, network, and exec are a liability. You need sandboxing at the language level — not afterthought middleware.

LLMs mit Dateizugriff, Netzwerk und exec sind ein Risiko. Du brauchst Sandboxing auf Sprachebene — kein nachträgliches Middleware-Gefrickel.

🐌

Performance

Performance

Sequential API calls turn a 1-second pipeline into a 10-second bottleneck. Parallelism shouldn't require asyncio.gather() boilerplate.

Sequentielle API-Calls machen aus einer 1-Sekunden-Pipeline einen 10-Sekunden-Flaschenhals. Parallelismus sollte kein asyncio.gather()-Boilerplate brauchen.

🔗

Vendor Lock-in

Vendor-Lock-in

Switching from OpenAI to DeepSeek means rewriting your SDK code. Provider changes should be one line — not a refactor.

Von OpenAI zu DeepSeek wechseln heißt SDK-Code umschreiben. Provider-Wechsel sollten eine Zeile sein — kein Refactor.

Pipe fixes this at the language level.<br>Pipe löst das auf Sprachebene.

From log files to AI agents — in a few lines

Von Logdateien bis KI-Agenten — in wenigen Zeilen

Log Analysis → Incident Report

Log-Analyse → Incident-Report

Read server logs, classify severity with AI, filter critical entries, summarize findings, translate to German, and save — 5 lines. No intermediate files. No Python script.

Server-Logs einlesen, Schweregrad per KI klassifizieren, kritische Einträge filtern, zusammenfassen, ins Deutsche übersetzen und speichern — 5 Zeilen. Keine Zwischendateien. Kein Python-Skript.

is_critical: fn line<br>contains line "critical"

read_file "/var/log/app/errors.log"<br>> split "\n"<br>> filter is_critical<br>> summarize<br>> translate "de"<br>> save "incident_report.txt"

RAG Pipeline — Context-aware Q&A

RAG-Pipeline — Kontextbezogene Q&A

Vectorize documents, find matches by meaning — not keywords. Built-in embed, nearest, cosine_sim. Works with every provider: OpenAI, DeepSeek, Anthropic, Ollama. No vector DB setup.

Dokumente vektorisieren, Treffer nach Bedeutung finden — nicht nach Stichwörtern. Eingebaute embed, nearest, cosine_sim. Funktioniert mit jedem Provider: OpenAI, DeepSeek, Anthropic, Ollama. Keine Vektor-DB.

ai_provider "deepseek"

docs: read_lines "knowledge_base.txt"<br>vectors: embed_batch docs

question: "How does the bytecode VM work?"<br>q_vec: embed question<br>top: nearest q_vec vectors 3

context: ""<br>for idx in top<br>context: context ++ (at docs idx) ++ "\n---\n"

ask ("Context:\n" ++ context ++ "\nQuestion: " ++ question)<br>> print

AI Agents — Sandboxed & Parallel

KI-Agenten — Sandboxed & Parallel

Define a tool, register it with the LLM, and let the model call it autonomously. Sandbox profiles lock down exec, write_file, and network access — safe by default. The same code swaps between OpenAI, DeepSeek, and Ollama with one line.

Ein Tool definieren, beim LLM registrieren und das Modell autonom aufrufen lassen. Sandbox-Profile sperren exec, write_file und Netzwerkzugriff — standardmäßig sicher. Derselbe Code wechselt mit einer Zeile zwischen OpenAI, DeepSeek und Ollama.

-- Declare a sandbox: temp files only, network ok, no exec<br>sandbox_profile "agent" {fs: "temp-only", network: true, exec: false, ai: true}<br>set_sandbox "agent"

fn get_weather city<br>match city<br>| "Berlin" -> "22°C, sunny"<br>| "London" -> "15°C, rainy"<br>| _ -> city ++ ": no data"

ai_tool "get_weather" "Get current weather for a city" {city: "City name"} get_weather

ai_with_tools "You are a weather assistant." "What's the weather in Berlin and London?"<br>> print

MCP-Native — Connect any MCP server

MCP-Nativ — Beliebige MCP-Server einbinden

Pipe is the first language with built-in MCP — both server and client. Connect to 100+ community servers off npm/uvx, expose your own tools to Claude Desktop, and use everything together in...

pipe pipeline deepseek openai server exec

Related Articles