Skip to main content

Tools

AutoGen

61,956

Multi-agent conversation framework with programmable group chats.

Upstream archived. The repository of AutoGen is read-only: it gets no further changes. Upstream is archived (checked on GitHub 2026-11-21; last push 2026-11-12). The repository README says the project "has been archived and is no longer actively maintained by Microsoft" and names Microsoft Agent Framework (github.com/microsoft/agent-framework) as the successor; that project is not a node here. Licence: code MIT (LICENSE-CODE), documentation CC-BY-4.0 (LICENSE). Status set to deprecated.

Prevention Pre-generation Fully autonomous Hybrid Deprecated Upstream archived Activity band F PromptEnvironment
Activity band details

Activity band A to F: a bin of a score that adds GitHub stars (log scale), a push to the upstream repository in the 12 months before `as_of`, the number of declared integration surfaces and, where the catalogue records them, citing papers and benchmark evaluations. It measures popularity and activity. It is not a level of evidence: no band means a paper cites the tool or that it was measured. Recency is judged as of 2026-11-22.

Computed band: F (raw score 7.42). Shown band: F .

Facets: documented_in=0evaluated_on=0integration_surfaces=0.5paper_citations=3recent_push=2stars=1.92

capped from A to F by maturity_status='deprecated'

Source of truth: pipeline/maturity/score.py

Description

Microsoft Research open-source framework for building LLM applications as conversations between configurable agents (AssistantAgent, UserProxyAgent, GroupChat). Supervision primitives: per-agent system message scoping, conversable-agent turn control, code-execution config that gates whether an agent may run tools or code and in what environment, and GroupChatManager for bounded multi-agent discussion. v0.4 rewrote the core as an actor-model runtime (AgentChat on top of autogen-core).

Why it's included

Occupies prevention × pre_generation × fully_autonomous for the conversation-centric multi-agent archetype. AutoGen scopes behavior via per-agent system messages and turn protocols rather than explicit role/task contracts, which is worth separating in the taxonomy.

Security notes

Open-source (MIT) from Microsoft Research. UserProxyAgent can execute code — configure code_execution_config to run inside a container (Docker) rather than on the host, or disable execution entirely for untrusted prompts. Check compatibility across the 0.2 → 0.4 rewrite when auditing existing integrations; the APIs are not identical.

Addresses failure modes

These tags are the catalog's claim about what AutoGen is built to catch or prevent. A tag is not a test result. SAICA-Bench has not measured AutoGen, so none of these tags is tested here.

  • Scope creep — Actions outside declared task boundary.

Records evidence of

AutoGen can record evidence of these failures (traces, or checks you configure yourself), but it does not detect or prevent them on its own. They are not counted as failure modes it addresses.

Techniques

conversable-agentsgroup-chat-managercode-execution-configactor-runtimesystem-message-scoping

Citations

Cited in

View raw YAML on GitHub →