// Trust & Security Report

    OpenBMB (Open Lab for Big Model Base) / Tsinghua University NLP Lab logo

    OpenBMB (Open Lab for Big Model Base) / Tsinghua University NLP Lab

    ChatDev 2.0 (DevAll): Open-source zero-code multi-agent orchestration platform for LLM-powered workflow automation. Includes legacy ChatDev v1.0 for software development teams.

    Certifications held

    0

    Maturity

    Startup

    Trains on your data

    No

    Trust center

    No

    // Certification ledger

    Each held certification is backed by a verbatim quote from the vendor's own trust or security page. “Not confirmed” means we could not verify it publicly, not that the vendor lacks it.

    > Show 6 unconfirmed / not-held certifications
    SOC 2 Type 1/2
    NOT CONFIRMED

    No public evidence of SOC 2 certification. ChatDev is open-source software, not a commercial SaaS service, so SOC 2 does not apply to the project itself. Users' deployments are their own responsibility.

    source: github.com
    ISO 27001
    NOT CONFIRMED

    No public evidence of ISO 27001 certification. ChatDev is open-source software. OpenBMB and affiliated organizations (Tsinghua University, BAAI) are not publicly documented as ISO 27001 certified.

    source: github.com
    GDPR Compliance
    NOT CONFIRMED

    Not applicable. ChatDev is open-source software deployed on user infrastructure. No personal data processing by the vendor.

    source: github.com
    HIPAA
    NOT CONFIRMED

    Not applicable. ChatDev is open-source software. Users deploying ChatDev in regulated environments (healthcare) are responsible for their own HIPAA compliance.

    source: github.com
    PCI DSS
    NOT CONFIRMED

    Not applicable. ChatDev is open-source software. PCI DSS compliance depends on user deployment.

    source: github.com
    ISO 27017/27018 (Cloud Security)
    NOT CONFIRMED

    Not applicable. ChatDev is open-source, user-deployed software, not a cloud service provided by the vendor.

    source: github.com

    // Privacy & AI training

    Trains on customer data

    No

    Data processing agreement

    Not offered

    Data region

    N/A - user-hosted open-source software

    ChatDev is a multi-agent orchestration platform, not a model trainer. Users' workflows and data are not ingested by OpenBMB. Users can configure ChatDev to use third-party LLM APIs (OpenAI, Anthropic, Gemini, etc.); compliance depends on which LLM provider is configured.

    // Security controls

    License & Open Source Audit

    Apache 2.0 (permissive). Full source code available for review on GitHub. 199 commits, 73 contributors, 33.6k stars. Active development.

    github.com

    Self-Hosting Model

    ChatDev is designed for self-hosting. Users deploy via Docker Compose, Python/uv, or direct Python execution. No vendor-managed SaaS infrastructure.

    github.com

    Encryption in Transit (TLS)

    Depends on user deployment. Backend is FastAPI (Python), frontend is Vue 3. Users are responsible for TLS/HTTPS configuration in their own environment.

    github.com

    Data Storage

    ChatDev includes YAML workflow configs and in-memory session data. No vendor-managed database. Users control where YAML files and workflow artifacts are stored. Artifacts are generated in local 'WareHouse/' directory.

    github.com

    Authentication

    No built-in user authentication in open-source ChatDev. Users deploying ChatDev for multi-user access are responsible for adding authentication/authorization (via reverse proxy, IAM, etc.).

    github.com

    LLM API Keys

    ChatDev requires users to provide LLM API keys (OpenAI, Anthropic, Gemini, etc.). Keys are configured via .env file. Users are responsible for key rotation and secure storage.

    github.com

    // Products & data scope

    ChatDev 2.0 (DevAll)Multi-Agent Orchestration Platform

    data: Workflow YAML configs, workflow artifacts (generated code, data visualizations, 3D models), session logs. All user-controlled, locally stored.

    Zero-code platform. Users define agents, workflows, and tasks via YAML. Supports out-of-the-box templates for data visualization, 3D generation (Blender), game dev, deep research, and video generation.

    ChatDev 1.0 (Legacy)Software Development Multi-Agent System

    data: Software development tasks, generated code, documentation. User-deployed.

    Moved to chatdev1.0 branch. Simulates a virtual software company with specialized agent roles (CEO, CTO, Programmer, Tester, etc.). No longer the primary focus.

    ChatDev Python SDKProgrammatic Orchestration

    data: Workflow execution via Python. Outputs and results handled by user code.

    PyPI package 'chatdev' (v0.1.0+). Users can orchestrate workflows programmatically rather than via the web console.

    // What to watch

    • ChatDev is NOT a commercial SaaS vendor. It is an open-source project. Traditional vendor compliance metrics (SOC 2, ISO 27001, GDPR, HIPAA, DPA) do not apply to the open-source project itself.
    • Users deploying ChatDev are responsible for their own compliance. Compliance posture depends entirely on deployment context (on-premises, cloud, LLM provider choice).
    • No vendor trust center, security documentation, or privacy policy exists. This is normal for open-source projects.
    • LLM Provider Risk: ChatDev is configured to use third-party LLM APIs (OpenAI, Anthropic, Gemini). Users' workflows and prompts are sent to the configured LLM provider. Compliance with user's data policies depends on which LLM is selected and that provider's terms.
    • No built-in user authentication. Multi-user deployments require additional security controls (reverse proxy, IAM, etc.).
    • OpenBMB is academically affiliated (Tsinghua University, BAAI, Beijing) with a related commercial entity (ModelBest, founded 2022). ChatDev itself remains open-source.

    // At a glance

    Pricing model

    Open-source (free). No commercial SaaS offering. Users pay for third-party LLM API usage (OpenAI, Anthropic, etc.) and infrastructure costs.

    Self-hostable

    Yes

    // How we verified this

    Every certification marked HELD is confirmed against a verbatim quote on OpenBMB (Open Lab for Big Model Base) / Tsinghua University NLP Lab's own trust, security, or privacy pages. We reject certifications claimed only on third-party aggregators, on a cloud host's behalf, or by a similarly named company.

    Last verified 2026-07-06. Compliance changes over time. Always confirm directly with the vendor before relying on any certification for a purchasing or compliance decision.

    github.com

    > Browse all vendor trust reports