Agency Swarm
Python framework for multi-agent applications where agents with defined roles talk through explicit flows, built on the OpenAI Agents SDK.
Harness by VRSEN
Chalk Labs
Need help deploying Agency Swarm?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
From the package registry. Read the repository before you give any tool access to your data.
pip install agency-swarm
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-orchestration
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Languages
- PythonREADME
- Packages
- agency-swarm (pypi)README
- Multi-agent
- YesREADME
- Orchestration
- otherREADME
- Memory
- short-term, long-termREADME
- Model providers
- openai, anthropic, google, xai, azure-openaiREADME
- Maturity
- StableREADME
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.
Alternatives
Frameworks for the same language with a similar way of orchestrating agents.
- 0.729score
Agent Squad
2FastLabs
Open-source framework that routes each user query to one of several AI agents, with Python, TypeScript and Swift runtimes.
HarnessAFreshness: A★ 7.8K↓ 1.5K/wk - 0.715score
Pipecat
Daily
Open-source Python framework for real-time voice and multimodal agents, built from composable pipelines with handoffs between specialist agents.
HarnessAFreshness: A★ 16.8K↓ 373.6K/wk - 0.667score
OGX (formerly Llama Stack)
OGX
OpenAI-compatible agentic API server for inference, vector stores, files and skills, on any model or infrastructure.
HarnessAFreshness: A★ 8.4K↓ 14.2K/wk - 0.650score
txtai
NeuML
All-in-one Python AI framework for embeddings-based semantic search, LLM pipelines, workflows and agents.
HarnessAFreshness: A★ 13K↓ 3.3K/wk - 0.607score
Microsoft Agent Framework
Microsoft
Open framework for building and hosting production-grade AI agents and multi-agent workflows in .NET and Python.
HarnessAFreshness: A★ 14.3K↓ 47.6K/wk
Signals
- Stars
- 4,614
- Forks
- 1,057
- Open issues
- 3
- Weekly downloads
- 757
- Last commit
- Oct 21, 2026 (9 days ago)
- Last release
- Aug 3, 2026 (2 months ago)
- Last package publish
- Aug 3, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Packages
- pypi
agency-swarm - License
- MIT
- Repository
- github.com/VRSEN/agency-swarm
- Website
- agency-swarm.ai/
- Docs
- agency-swarm.ai/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- READMEDocsgithub-graphql
More from VRSEN
- 0.626score
AGENTS.md · VRSEN/agency-swarm
VRSEN
AGENTS.md from VRSEN/agency-swarm: 47 lines covering 1.
TemplateAFreshness: A★ 4.6KCodex +5 - 0.613score
Cursor rules · VRSEN/agency-swarm
VRSEN
1 Cursor rule file from VRSEN/agency-swarm: writing-docs.
TemplateAFreshness: A★ 4.6KCursor - 0.586score
instructions-writer
VRSEN
Subagent "instructions-writer" from VRSEN/agency-swarm: Write optimized agent instructions using prompt engineering best practices
TemplateBFreshness: B★ 4.6KClaude Code - 0.586score
prd-creator
VRSEN
Subagent "prd-creator" from VRSEN/agency-swarm: Transform ideas into comprehensive PRDs optimized for parallel agent creation
TemplateBFreshness: B★ 4.6KClaude Code - 0.586score
agent-creator
VRSEN
Subagent "agent-creator" from VRSEN/agency-swarm: Create complete agent modules with folder structure per Agency Swarm v1.0.0 spec
TemplateBFreshness: B★ 4.6KClaude Code - 0.586score
tools-creator
VRSEN
Subagent "tools-creator" from VRSEN/agency-swarm: Implement and test tools with MCP servers preferred, runs after agent files exist
TemplateBFreshness: B★ 4.6KClaude Code
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Agency Swarm running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Agency Swarm. Agent Mart. https://agentmart.dev/harnesses/agency-swarm (last updated 2026-10-24)