English | 简体中文

Interested in Tandem Hosted? Join the waitlist

The governed runtime for AI-first companies

Tandem is a source-available governed runtime for AI-first work. It gives solo builders, startups, and platform teams a deployable authority layer that controls what agents can see, which tools they can discover, which actions they can execute, when humans must approve, and what evidence survives.

The model is not the access-control perimeter. Tandem enforces authority below the model through scoped execution, tenant-aware state, permissioned memory, approval gates, and audit trails. Agents work inside projected authority; the runtime owns state, tools, approvals, memory, artifacts, and evidence.

Tandem is not another chat wrapper, and it is not just an agent framework. It is the execution runtime underneath agents as they move from answering questions to acting on company systems.

• Entrypoints are clients, not separate engines: The Tauri desktop app, TUI, web control panel, channels, and SDKs all talk to the same engine runtime.
• Runtime-owned authority: Runs, sessions, memory, context, provider secrets, MCP tools, approvals, artifacts, and audit records live below the model.
• Governed tool execution: Built-in tools and MCP connectors can be scoped per workflow step, with approval gates for consequential actions.
• Tenant-aware runtime: Hosted and enterprise modes carry tenant/principal context through sessions, runs, context runs, memory, provider credentials, MCP secrets, and events.
• Deployable where the data lives: Tandem can run locally, headlessly, hosted, or inside customer infrastructure.
• Provider agnostic: Use OpenRouter, Anthropic, OpenAI, OpenCode Zen, or local Ollama endpoints.

Intent -> Authority Projection -> Scoped Execution -> Approval Gates -> Artifacts -> Audit Trail

-> AI runtime infrastructure | Enterprise readiness | EU AI Act readiness | Compliance starter pack | Connect an agent via MCP

Why Tandem Exists

Agents are becoming workers. They read company context, call tools, open pull requests, draft customer communication, operate project boards, and prepare decisions that used to stay inside human-only systems.

Prompts are not permissions. A system prompt can ask a model to avoid a tool, skip a folder, or wait for approval, but the model should not be the security boundary. Tandem puts those controls in a runtime that can project authority into an agent's work and deny actions outside that authority.

Companies also need central AI context without flat access. A permissioned company memory should know what the company knows, but an agent acting for one team, tenant, project, or user should only retrieve the slice it is allowed to use.

What Tandem Governs

• Company knowledge and memory: Runtime-owned memory, knowledge spaces, and retrieval paths designed around tenant and workspace boundaries.
• Tool and MCP visibility: Step-scoped built-in tools and MCP connector tools, with broader pre-invocation masking planned for enterprise deployments.
• Workflow execution: Durable automation and context-run state instead of fragile transcript-only execution.
• Human approvals: Runtime gates pause runs, collect approve/rework/cancel decisions, and leave evidence.
• Tenant and workspace boundaries: Tenant-aware sessions, runs, context runs, events, provider credentials, MCP secrets, memory, and contract vocabulary for resource scopes and grants.
• Connector credentials and secrets: Provider and MCP secret references are runtime-owned; connector source binding gives scoped ingestion a shared contract as that layer matures.
• Artifacts and audit trails: Outputs, validations, tool ledger events, approval decisions, and protected audit records survive outside the model context window.

Core Use Cases

Use case	What Tandem adds
Approval-gated email and workflows	Agent proposes work, Tandem pauses before the action, a human approves or requests rework.
Permissioned company knowledgebase	Company memory and knowledge spaces with tenant-aware retrieval and resource-grant vocabulary.
Governed coding agents	Coder runs, worktree context, handoff artifacts, approval points, and auditable implementation state.
Project, sprint, and event brain	Long-running context, tasks, artifacts, and memory that survive across sessions and teams.
Tenant-isolated hosted automations	Hosted runtime records, event streams, provider credentials, MCP secrets, and memory scoped by tenant.
Internal agent and tool governance	A control point for which agents can see which tools, execute which actions, and leave which evidence.

Why Platform And Security Teams Care

Tandem is designed for teams that need to run AI work under real operational controls:

• Runtime authority, not prompt authority: The model can request context or a tool call; the runtime decides what is visible and executable.
• Tenant-aware records: Sessions, automation runs, context runs, event streams, provider credentials, MCP secrets, and memory paths carry tenant context in hosted/shared modes.
• Resource and grant model: The enterprise contract includes ResourceRef, ResourceKind, ResourceScope, AccessPermission, DataClass, PrincipalRef, ScopedGrant, StrictTenantContext, and DataBoundary.
• Permissioned memory: Memory and knowledge paths carry tenant boundaries so company knowledge can become useful without becoming globally flat.
• Deployable runtime: The same runtime can run on a laptop, as a headless engine, hosted, or inside customer infrastructure as the enterprise layer matures.
• Auditability: Approval decisions, policy denials, provider secret changes, MCP activity, tool ledger events, artifacts, and protected audit records can be inspected outside chat transcripts.

Deployment Model

Tandem is useful locally and grows toward stricter company deployments:

• Local desktop: Single-user desktop runtime with local workspace scope, provider setup, and approval-gated tools.
• Headless engine: tandem-engine serve for SDKs, control panels, automations, and CI/dev environments.
• Hosted/private managed: Hosted deployments with transport-token and signed context assertions for tenant-aware access.
• Customer infrastructure: A deployment model for running where company data, connector credentials, and operational evidence need to live.

Current Status

Current capabilities	Enterprise roadmap
Runtime auth modes: local_single_tenant, hosted_single_tenant, enterprise_required	Full RBAC, OIDC, SCIM, SIEM integrations, SOC2 package, and enterprise identity policy bridge
Tenant context and signed context assertions for hosted/enterprise ingress	Private enterprise sidecar with fail-closed policy authorization
Tenant-aware sessions, automation runs, context runs, events, coder routes, and memory APIs	Complete artifact/export isolation across every path
Provider credential and MCP secret tenant boundaries	Full tool-discovery masking before model invocation
Memory tenant partitioning, tenant-scoped knowledge spaces, and resource-scoped retrieval APIs	Production connector ingestion admin platform with live external source ingestion
Resource access-control contract types and strict context projection vocabulary	Signed approval receipts and auditor-grade immutable receipt chains
Approval gates, pending approval inbox, channel approvals, tool ledger events, and audit records	Advanced connector quarantine/revoke/rotate operations wired to production ingestion workflows

Compliance and AI Act readiness

Tandem helps teams operate AI workflows with human oversight, scoped tools, durable execution evidence, and protected-action controls. For regulated or security-sensitive deployments, start with the EU AI Act readiness brief, then use the Compliance Starter Pack for control mapping, Article 50 transparency guidance, deployer instructions, an Annex IV documentation template, and a limitations/responsibility matrix.

30-second quickstart

Web Control Panel

Install the master CLI, then bootstrap the panel and its engine service:

npm i -g @frumu/tandem
tandem install panel
tandem panel init
tandem panel open

Use this when you want the browser-based control center backed by the engine.

For local installs, you can now open Settings -> Providers -> openai-codex and choose Connect Codex Account to sign in through the browser instead of pasting an OpenAI API key.

Desktop

1. Download and launch Tandem: tandem.ac
2. Open Settings and add a provider API key, or use the local control panel to connect a Codex account for openai-codex.
3. Select a workspace folder.
4. Start with a task prompt and choose Immediate or Plan Mode.

Editable App Scaffold

Generate a fully editable control panel app in your own folder:

npm create tandem-panel@latest my-panel
cd my-panel
npm install
npm run dev

Use this when you want to customize routes, pages, themes, styles, or runtime behavior without editing node_modules.

MCP-assisted setup

If you want an existing agent to help install or configure Tandem, connect that agent to Tandem's MCP interface first. The MCP docs explain how to wire your own agent into Tandem so it can assist with setup, configuration, and follow-up tasks:

• Tandem MCP docs

If you only want the engine runtime, you can keep it foreground-only:

tandem-engine serve --hostname 127.0.0.1 --port 39731

Other Entry Points

• TUI: npm i -g @frumu/tandem-tui && tandem-tui
• SDKs: npm install @frumu/tandem-client or pip install tandem-client

Codex And Docker Setup

• Codex users can connect Tandem through the tandem-codex-plugin repository.
• For a Docker-based Tandem agents setup, see tandem-agents.

Open Core & Source-Available Architecture

Tandem is built for developers first, using an open-core model. We believe that to trust an AI runtime, you must be able to audit the execution router line-by-line.

Local Development & Internal Use: The core Rust execution engine, local desktop app, and tandem-agents libraries are free for local development and internal deployment.

Enterprise Path: Advanced features for scaled organizational deployments, such as enterprise identity federation, richer policy enforcement, signed receipt chains, private sidecar enforcement, SIEM export, and HA packaging, are planned enterprise capabilities and may be governed under commercial or source-available terms, including the Business Source License 1.1 (BUSL-1.1) where declared.

License Boundary: You are free to use Tandem to govern your own agents under the license terms for each package. Source-available Tandem components cannot be wrapped and sold as a managed competitive SaaS unless your license permits it. See docs/LICENSING.md for exact details.

Architecture

flowchart TD
    Human[Human operator or team]

    subgraph Entrypoints["Entrypoints: clients, not authority boundaries"]
        Desktop[Desktop app]
        Panel[Web control panel]
        TUI[Terminal UI]
        SDK[TypeScript / Python SDKs]
        Channels[Slack / Discord / Telegram]
    end

    subgraph Agents["Agents and models: propose, reason, draft"]
        Workers[Agent workers]
        Models[OpenAI / Anthropic / OpenRouter<br/>OpenCode Zen / Ollama]
    end

    subgraph Tandem["Tandem governed runtime: owns authority"]
        API[HTTP/SSE API]
        Tenant[Auth mode, tenant context<br/>and authority chain]
        Projection[Authority projection<br/>resources, grants, data classes]
        Runs[Sessions, workflows<br/>automations, context runs]
        Gates[Human approval gates]
        Policy[Tool and MCP policy]
        Memory[Permissioned memory<br/>and company knowledge]
        Secrets[Provider and MCP secrets]
        Artifacts[Artifacts, validation<br/>and run evidence]
        Audit[Audit trail and tool ledger]
    end

    subgraph Systems["Company systems and data"]
        Workspace[Workspace files and repos]
        MCP[MCP servers and connectors]
        Data[Customer / company data]
        Browser[Browser and external tools]
    end

    Human --> Desktop
    Human --> Panel
    Human --> TUI
    Human --> SDK
    Human --> Channels

    Desktop --> API
    Panel --> API
    TUI --> API
    SDK --> API
    Channels --> API

    API --> Tenant
    Tenant --> Projection
    Projection --> Runs
    Runs <--> Workers
    Workers <--> Models

    Runs --> Gates
    Runs --> Policy
    Runs --> Memory
    Runs --> Artifacts
    Gates --> Audit
    Policy --> Audit
    Artifacts --> Audit

    Policy --> Secrets
    Policy --> Workspace
    Policy --> MCP
    Policy --> Data
    Policy --> Browser
    Memory --> Data

Loading

Common workflows

Governed workflow	What the Tandem runtime controls
Evaluate vendor or policy risk	Read selected sources, draft cited artifacts, validate limitations, and keep mutation tools outside the read step.
Approval-gated email or updates	Let an agent draft the action, pause at a human gate, resume only after approve/rework/cancel evidence is recorded.
Execute code migrations	Track coder runs, worktree state, changed files, validation, handoff artifacts, and approval points.
Govern external MCP tools	Scope connector tools by workflow step, require concrete tool evidence, and isolate MCP secrets by tenant path.
Permissioned company memory	Retrieve company context through runtime-owned memory and knowledge spaces instead of pasting everything into chat.
Tenant-isolated hosted workflows	Keep sessions, runs, events, credentials, MCP secrets, and memory partitioned by tenant in hosted/shared modes.

Features

Governed execution

• Model is not the control system: The model can propose work; Tandem owns the allowed tools, context, state transitions, approvals, and audit evidence.
• Scoped workflow execution: Automation V2 nodes can carry built-in tool and MCP connector policy so different steps see different capabilities.
• Approval-gated actions: Runs can halt before consequential work, wait for approve/rework/cancel decisions, and resume with recorded gate history.
• State Survival: Checkpoints, replayable event history, and materialized run states that survive API timeouts and connector failures.

Permissioned memory and company knowledge

• Tenant-partitioned memory: Vector-backed session, project, global, and file-import memory paths carry tenant scope.
• Knowledge spaces: Curated knowledge spaces and items can be managed through tenant-aware APIs.
• Runtime retrieval: Agents retrieve context through the runtime, creating a path toward permissioned company memory instead of flat transcript stuffing.

Tenant and workspace isolation

• Tenant-aware records: Sessions, automation definitions/runs, context runs, event streams, provider credentials, MCP secret references, memory, and coder routes carry tenant context.
• Strict context contract: Resource refs, scoped grants, data classes, principals, and data boundaries are modeled in the enterprise contract.
• Local behavior preserved: Local/default single-tenant usage remains the default for desktop and developer workflows.

MCP and tool governance

• MCP connector support: Tandem can connect to MCP servers, sync tools, and scope selected connector tools to workflow nodes.
• Secret isolation: Store-backed MCP secret references validate tenant scope before resolution in hosted/shared paths.
• Tool discovery as an authority surface: Tool discovery and MCP visibility are governed by runtime policy; full masking of unauthorized tools before model invocation remains enterprise roadmap work.

Human approval gates and audit

• Approvals inbox and channel approvals: Operators can approve, request rework, or cancel from runtime-owned approval surfaces.
• Durable evidence: Tool ledger events, gate history, artifacts, validation metadata, and protected audit events can survive outside the model context window.
• Audit stream: Admin-facing audit streams and protected audit envelopes exist; immutable receipt chains and signed approval receipts remain roadmap work.

Multi-agent orchestration

• Kanban-driven execution: Agents claim tasks, report blockers, and hand off work through deterministic state.
• Memory-aware workers: Agents can use prior run context, project memory, and knowledge spaces through runtime paths.
• Revisioned coordination: Engine-enforced locks prevent agents from trampling the same codebase simultaneously.

Local and self-hosted controls

• MCP tool connectors
• Scheduled automations and routines
• Headless runtime with HTTP + SSE APIs
• Desktop runtime for Windows, macOS, and Linux
• API keys encrypted in local SecureKeyStore (AES-256-GCM)
• Local Codex OAuth credentials stay engine-owned; browser UIs initiate sign-in but do not persist refresh tokens
• Workspace access is scoped to folders you explicitly grant
• Write/delete operations require approval via supervised tool flow
• Sensitive paths denied by default (.env, .ssh/*, *.pem, *.key, secrets folders)
• No analytics or call-home telemetry from Tandem itself

Outputs and artifacts

• Markdown reports
• HTML dashboards
• PowerPoint (.pptx) generation

Enterprise Path And Roadmap

Tandem already includes the runtime building blocks for governed AI work in hosted and self-managed environments. The next enterprise capabilities strengthen identity, policy, audit export, and administration around those building blocks.

Available now:

• Runtime auth modes and hosted/enterprise signed context assertion verification.
• Tenant-aware sessions, runs, context runs, event streams, provider credentials, MCP secrets, memory, and coder routes.
• Resource access-control contract vocabulary for resources, scopes, principals, grants, data classes, and data boundaries.
• Approval gates, protected audit records, audit streams, tool ledger events, and runtime artifacts.
• Connector source-binding contracts using secret references, resource refs, data classes, quarantine/revoke/rotate vocabulary, and scoped memory chunk references.

Planned enterprise capabilities:

• Full RBAC, OIDC/SSO, SCIM, SIEM export, SOC2 package, and enterprise admin workflows.
• Private enterprise sidecar and policy bridge with required-mode fail-closed enforcement.
• Signed approval receipts, immutable receipt chains, and broader audit/export isolation.
• Full tool-discovery masking before model invocation.
• Complete external connector ingestion admin platform and production ingestion flows.

Programmatic API

The SDKs are API clients. They do not bundle tandem-engine.
You need a running Tandem runtime (desktop sidecar or headless engine) and then use the SDKs to create sessions, trigger runs, and stream events.

Runtime options:

• Desktop app running locally (starts the sidecar runtime)

• Headless engine via npm:

  npm install -g @frumu/tandem
  tandem-engine serve --hostname 127.0.0.1 --port 39731

• TypeScript SDK: @frumu/tandem-client

• Python SDK: tandem-client

• Engine package: @frumu/tandem

// npm install @frumu/tandem-client
import { TandemClient } from "@frumu/tandem-client";

const client = new TandemClient({ baseUrl: "http://localhost:39731", token: "..." });
const sessionId = await client.sessions.create({ title: "My agent" });
const { runId } = await client.sessions.promptAsync(sessionId, "Summarize README.md");

for await (const event of client.stream(sessionId, runId)) {
  if (event.type === "session.response") process.stdout.write(event.properties.delta ?? "");
}

# pip install tandem-client
from tandem_client import TandemClient

async with TandemClient(base_url="http://localhost:39731", token="...") as client:
    session_id = await client.sessions.create(title="My agent")
    run = await client.sessions.prompt_async(session_id, "Summarize README.md")
    async for event in client.stream(session_id, run.run_id):
        if event.type == "session.response":
            print(event.properties.get("delta", ""), end="", flush=True)

Provider setup

Configure providers in Settings.

Provider	Description	Get API key
OpenAI Codex Account	Browser sign-in for local Codex-account usage	Local control panel: Settings -> Providers -> openai-codex
OpenRouter ⭐	Access many models through one API	openrouter.ai/keys
OpenCode Zen	Fast, cost-effective models optimized for coding	opencode.ai/zen
Anthropic	Anthropic models (Sonnet, Opus, Haiku)	console.anthropic.com
OpenAI	GPT models and OpenAI endpoints	platform.openai.com
Ollama	Local models (no remote API key required)	Setup Guide
Custom	OpenAI-compatible API endpoint	Configure endpoint URL

Notes:

• openai-codex is currently intended for local engine-backed Tandem setups.
• Standard OpenAI API keys remain supported for the normal openai provider.

Web search setup

websearch can now be configured directly from:

• Desktop: Settings -> Web Search
• Control panel: Settings -> Web Search when connected to a local managed engine

Recommended default:

• Backend = auto
• add a Brave key, an Exa key, or both

auto prefers configured providers and can fall through across backends instead of pinning the engine to a single hosted search path. For headless installs you can still configure this through env vars:

TANDEM_SEARCH_BACKEND=auto
TANDEM_BRAVE_SEARCH_API_KEY=...
TANDEM_EXA_API_KEY=...
TANDEM_SEARXNG_URL=http://127.0.0.1:8080
TANDEM_SEARCH_URL=https://search.tandem.ac

If Brave is rate-limited and Exa is configured, auto can continue with Exa instead of immediately surfacing search as unavailable.

Design principles

• Local-first runtime: Data and state stay on your machine unless you send prompts/tools to configured providers.
• Supervised execution: AI runs through controlled tools with explicit approvals for write/delete operations.
• Provider agnostic: Route through the model providers you choose.
• Auditable source with clear license boundaries: This is a mixed-license repository: permissive MIT, Apache-2.0, and MIT OR Apache-2.0 components sit alongside source-available BUSL-1.1 compiler and governance components, as documented in docs/LICENSING.md.

Security and privacy

• Telemetry: Tandem does not include analytics/tracking or call-home telemetry.
• Provider traffic: AI request content is sent only to endpoints you configure (cloud providers or local Ollama/custom endpoints).
• Network scope: Desktop runtime communicates with the local sidecar (127.0.0.1) and configured endpoints.
• Updater/release checks: App update and release metadata flows can contact GitHub endpoints.
• Credential storage: Provider keys are stored encrypted (AES-256-GCM).
• Filesystem safety: Access is scoped to granted folders; sensitive paths are denied by default.

For the full threat model and reporting process, see SECURITY.md.

Learn more

• Architecture overview: ARCHITECTURE.md
• Engine runtime + CLI reference: docs/ENGINE_CLI.md
• Desktop/runtime communication contract: docs/ENGINE_COMMUNICATION.md
• Engine testing and smoke checks: docs/ENGINE_TESTING.md
• Docs portal: docs.tandem.ac

Advanced MCP behavior (including OAuth/auth-required flows and retries) is documented in docs/ENGINE_CLI.md.

Advanced setup (build from source)

Prerequisites

• Node.js 20+
• Rust 1.75+ (includes cargo)
• pnpm (recommended) or npm

Platform	Additional requirements
Windows	Build Tools for Visual Studio
macOS	Xcode Command Line Tools: xcode-select --install
Linux	libwebkit2gtk-4.1-dev, libappindicator3-dev, librsvg2-dev, build-essential, pkg-config

Local development

git clone https://github.com/frumu-ai/tandem.git
cd tandem
pnpm install
cargo build -p tandem-ai
pnpm tauri dev

Production build and signing notes

pnpm tauri build

For local self-built updater artifacts, generate your own signing keys and configure:

1. pnpm tauri signer generate -w ./src-tauri/tandem.key
2. TAURI_SIGNING_PRIVATE_KEY
3. TAURI_SIGNING_PASSWORD
4. pubkey in src-tauri/tauri.conf.json

Reference: Tauri signing documentation

Output paths:

# Windows: src-tauri/target/release/bundle/msi/
# macOS:   src-tauri/target/release/bundle/dmg/
# Linux:   src-tauri/target/release/bundle/appimage/

macOS install troubleshooting

If a downloaded .dmg shows "damaged" or "corrupted", Gatekeeper is usually rejecting an app bundle/DMG that is not Developer ID signed and notarized.

1. Confirm the correct architecture (aarch64/arm64 vs x86_64/x64).
2. Try opening via Finder (Right click -> Open or System Settings -> Privacy & Security -> Open Anyway).
3. For non-technical distribution, ship signed + notarized artifacts from release automation.

Contributing

Contributions are welcome. See CONTRIBUTING.md.

# Run lints
pnpm lint

# Run tests
pnpm test
cargo test

# Format code
pnpm format
cargo fmt

Engine-specific build/run/smoke instructions: docs/ENGINE_TESTING.md
Engine CLI usage reference: docs/ENGINE_CLI.md
Engine runtime communication contract: docs/ENGINE_COMMUNICATION.md

Maintainer release note

• Desktop binary/app release: .github/workflows/release.yml (tag pattern v*)
• Registry publish (crates.io + npm wrappers): .github/workflows/publish-registries.yml (manual trigger or publish-v*)
• The workflows are intentionally separate

Project structure

tandem/
├── src/                    # React frontend
│   ├── components/         # UI components
│   ├── hooks/              # React hooks
│   └── lib/                # Utilities
├── src-tauri/              # Rust backend
│   ├── src/                # Rust source
│   ├── capabilities/       # Permission config
│   └── binaries/           # Sidecar (gitignored)
├── scripts/                # Build scripts
└── docs/                   # Documentation

Support this project

If Tandem saves you time, consider sponsoring development.

❤️ Become a Sponsor

Star history

License

This repository uses a mixed licensing model. docs/LICENSING.md is the canonical package-by-package map.

• Core engine crates and tools (e.g. tandem-core, tandem-server, tandem-types, tandem-orchestrator, and others in crates/):

  • Licensed under MIT OR Apache-2.0 unless their manifest or local license says otherwise
  • See LICENSE-MIT and LICENSE-APACHE

• Mission compiler crate (tandem-plan-compiler):

  • Licensed under Business Source License 1.1 (BUSL-1.1)
  • See crates/tandem-plan-compiler/LICENSE for terms

• Governance engine crate (tandem-governance-engine):

  • Licensed under Business Source License 1.1 (BUSL-1.1)
  • See crates/tandem-governance-engine/LICENSE for terms

In short: Tandem is open core. The permissive runtime, protocol, SDK, and local tooling surfaces are open source, while the mission/plan compiler and recursive governance engine are source-available under Business Source License terms.

Acknowledgments

• Anthropic for the Cowork inspiration
• Tauri for the secure desktop framework
• The open source community