MetaGPT (harness)
https://github.com/FoundationAgents/MetaGPT
Cross-listing of MetaGPT as a harness. Multi-agent OSS framework that simulates a software company — PM, architect, engineer, QA. Generates docs + code + tests from a one-line prompt. ~44k★. Distinct from "Agent frameworks (no first-party memory layer)" row in framing.
At a glance
- Type
- Multi-agent software-company simulation (OSS)
- Tier
- T2
- Section
- Agent IDEs & coding harnesses
- Created
- 2023-06
- Latest release
- MetaGPT 0.x rolling
- License
- MIT
- GitHub
- ~44k★, Python
- Pricing
- Free (OSS)
- Funding
- not applicable — OSS / no commercial entity
Taxonomy
- storage
- file
- retrieval
- injection
- persistence
- cross-session
- update
- agent-controlled
- unit
- document
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: multi-agent role-play software-company simulation
Anti-fit: research-grade; not production-stable; output quality varies
Pros & cons
Pros
Most-starred multi-agent harness; defined the "agent-as-role" pattern many newer agents copy.
Cons
Research-grade output; weaker than focused coding agents (Devin/Cursor) on real-world tasks; documentation is mixed.
Claims & capabilities
~44k★; one of the highest-starred multi-agent frameworks; introduced "agent-as-role" pattern.
Technical surface
- API surface
- CLI + Python SDK
- Backend storage
- local workspace + role memory
- Deployment
- Self-host (pip)
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- single-user
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other agent ides & coding harnesses in the catalog, ranked by inbound references.
- Bedrock AgentCore (AWS) T2
AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).
- Claude Code (Anthropic) T1
Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as the reference harness for Claude-as-coder. Plan Mode and Compute Use surfaces extend it from coding to broader desktop automation.
- GitHub Copilot (Agent Mode) T1
The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.
- Aider (harness) T2
OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in "Coding-agent memory"; this row characterises the harness itself.
- Amazon Q Developer T1
Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows.
- Anthropic Computer Use T1
Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.
Related systems
References (3)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: OpenAI + Anthropic + Azure OpenAI
- Azure Machine Learning depends on at runtime — adjacent-infrastructure cell: OpenAI + Anthropic + Azure OpenAI
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — adjacent-infrastructure cell: OpenAI + Anthropic + Azure OpenAI