Linchpin / Compare / vs AutoGen

Linchpin vs AutoGen

AutoGen is Microsoft Research's Python library for multi-agent conversation. Linchpin is an HTTP-API agent runtime with per-session Docker sandboxes. Library vs runtime — different layers of the same stack.

What each one is

§ 01

AutoGen is a Python library from Microsoft Research for building applications around conversations between multiple agents. You define agents (each one an LLM with a system prompt and tools), then orchestrate them in group chats, sequential conversations, or nested team patterns. AutoGen v0.4+ rewrote the core for async + actor-style messaging. License is MIT. The library is imported into your own Python service.

Linchpin is an open-source managed-agent runtime. Three services plus Postgres on a single VM. Agents, environments, sessions, events are HTTP resources. Each session runs in its own Docker container with controlled networking. The append-only event log streams over SSE with cursor replay. Language-agnostic — anything that can curl can drive Linchpin. Apache-2.0.

Frame: AutoGen is code you import into a Python process. Linchpin is infrastructure you deploy and call over HTTP.

Side by side

§ 02
DimensionLinchpinAutoGen
What it isManaged-agent runtime (platform)Multi-agent conversation library
MaintainerOpen source community (linchpinhq)Microsoft Research
LicenseApache-2.0MIT (Creative Commons for docs)
LanguageHTTP API; runtime in PythonPython library
Deploymentdocker compose up on a VMImported into your Python app
Multi-agentRun multiple sessions; orchestrate from your codeFirst-class group chat / sequential / nested patterns
SandboxPer-session Docker container, per-env network policyOptional code-executor (Jupyter, Docker) you wire
Event logAppend-only Postgres, SSE replayConversation history in-process
Model providersOpenRouter (~200) + OllamaBroad (OpenAI, Azure, others via clients)
Streaming UISSE event stream out of the boxYou build it
PersistencePostgres by default — durable session stateIn-process unless you wire your own

When to pick Linchpin

§ 03

When to pick AutoGen

§ 04

Using them together

§ 05

They compose. AutoGen orchestrates the conversation pattern inside a Python service; Linchpin runs individual agents that need a sandbox (shell access, file ops, MCP tools). AutoGen calls Linchpin's HTTP API the way it would call any tool, and gets back streamed events from a real sandboxed session.

If your problem is "agents talking to each other" → AutoGen. If your problem is "agents executing tasks in isolated environments" → Linchpin. Many real apps are both.

Honest take

AutoGen v0.4 is sophisticated and well-resourced. Linchpin is small and focused. They aim at different problems — multi-agent topology vs single-agent runtime infrastructure. Pick by which one matches your bottleneck.

Related

§ 06