Teable - AI Spreadsheet for Business
Turn your data into AI workflows and custom apps that 100% fit your business, with the simplicity of a spreadsheet and the power of PostgreSQL.
- Source repo
- teableio/teable
- Stars
- ★ 22k
- Last updated
- 3d ago
- License
- NOASSERTION
- Primary language
- TypeScript
- FA score
- 53/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platform
- Cost
- Free tier plus a paid hosted plan
- Setup effort
- High · needs real infrastructure
- You'll need
- Typical use
- A small business owner needing a user-friendly database to track inventory with millions of rows without performance issues.
- Not a fit if
- Teams that need fully offline or air-gapped operation, since AI features rely on model providers
- Users wanting AI and App Builder on the free tier, as these need a paid license
- Individuals or small teams without Docker, PostgreSQL, and infrastructure operations experience
- Source review
- 53/100 · Major gaps
What does this agent do, and when should you use it?
Teable is an open-source, self-hostable platform that merges the simplicity of a spreadsheet with the robustness of PostgreSQL, offering data management, AI workflows, and app-building in one unified environment. It includes a secure agent sandbox, an app deployment platform, an AI workflow engine, and a full-featured database collaboration platform. AI capabilities enable natural language data interaction, AI-driven app generation, automated workflows, and field enrichment. Apps are built in isolated sandboxes and deployed as lightweight containers. Teable supports self-hosting with a community edition under AGPL-3.0, and offers multiple deployment options.
Teable provides a spreadsheet-like interface for creating and managing database tables, with multiple views including Grid, Form, Kanban, Gallery, and Calendar. It supports filtering, grouping, sorting, aggregation, formulas, field conversion, and handles millions of rows via PostgreSQL. The AI Chat feature lets users query and operate on data using natural language. The App Builder enables users to describe an app, which is then built by an AI agent in an isolated sandbox and deployed to a unique URL. AI automations react to record changes, schedules, and webhooks, incorporating AI reasoning. AI field filling generates or enriches field values in bulk. It also offers an API, SQL queries, comments, record history, real-time collaboration, import/export, and charting.
- A small business owner needing a user-friendly database to track inventory with millions of rows without performance issues.
- A business analyst who wants to ask questions of live data in natural language rather than writing SQL.
- An operations manager who needs to build custom internal tools quickly without waiting for IT.
- A team looking to automate workflows triggered by record changes or schedules, with AI steps for reasoning.
- An IT administrator in a regulated industry who requires self-hosting to keep data on-premises.
- A developer who wants to leverage a PostgreSQL backend with low-code app-building capabilities for rapid prototyping.
How do you install or deploy this agent?
For full self-hosting, use the teableio/teable-deployment repository with a domain, DNS token, and access to the target machine or cluster. Alternatively, follow the Docker guide for standalone deployment. For development, enable corepack, run 'pnpm install', initialize PostgreSQL with 'make switch-db-mode', set up environment variables, and run the backend with 'cd apps/nestjs-backend && pnpm dev'.
How do you use this agent?
You can start using Teable by signing up for the hosted cloud at teable.ai, or by self-hosting using the deployment guides. Once installed, create tables, add views, configure automations, and use AI chat for analysis. To use App Builder, describe the app you need; the agent builds it in a sandbox and deploys it to a URL. You can integrate via the documented API.
What are this agent's strengths and limitations?
- Built on PostgreSQL, offering robust performance and scalability for large datasets.
- AI features are deeply integrated with live data, not an isolated AI tool.
- Offers a spreadsheet-like interface with multiple views (grid, form, kanban, etc.) for flexible data interaction.
- Self-hosting provides full control over data and infrastructure, enhancing privacy and compliance.
- App Builder uses isolated containers for secure and scalable app deployment.
- AI features and App Builder are only available in the full-featured self-host or cloud, not standalone self-host, and may require a paid license.
- Deployment is complex, requiring knowledge of Docker, PostgreSQL, and infrastructure management.
- Community Edition is under AGPL-3.0, which may have implications for commercial use.
- Documentation and community support may be less mature than some commercial alternatives.
- AI capabilities depend on model providers, and there may be vendor lock-in for AI services.
How does this agent compare with similar options?
As an Airtable alternative, Teable differentiates itself by being open-source and self-hostable, whereas Airtable is a proprietary SaaS. Teable also emphasizes AI integration and app-building as core features.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Teable - AI Spreadsheet for Business This agent | 53 · Major gaps | Self-hosted serviceFreemium | ★ 22k | 3d ago | TypeScript | — |
| Telegram Search | 58 · Major gaps | Self-hosted serviceFree + model costs | ★ 4.1k | 1d ago | TypeScript | — |
| Nocturne Memory: Long-Term Memory Server for MCP Agents | 56 · Major gaps | MCP serverFree | ★ 1.4k | 26d ago | Python | — |
| WhoDB | 51 · Major gaps | Self-hosted serviceFreemium | ★ 5k | today | Go | — |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows: access tokens support fine-grained scopes (e.g., table|read, record|read) with tests verifying permission boundaries (least_privilege=2). User confirmation: AI features (e.g., App Builder) require user actions, but no explicit confirmation for each operation (user_confirmation=1). Data flow transparency: README describes AI sessions in isolated containers, but no detailed data flow (data_flow_transparency=1). Sensitive data handling: security policy and access token encryption exist, but no explicit sensitive data classification (sensitive_data_handling=2). Dependency security: dependency check scripts exist, but no vulnerability scanning evidence (dependency_security=1). External effects: AI features may make external calls, but no explicit restrictions (external_effects=1). Rollback: record history and undo/redo exist, but no explicit AI operation rollback (rollback=1). Source attribution: author info present, but publisher unverified (source_attribution=1).
Self-consistency: README, code, and tests are consistent; described features match implementation (self_consistency=2). Dependency availability: pnpm workspaces used, dependencies declared clearly, but not all dependencies verified available (dependency_availability=2). Failure messages: error handling in tests, but no user-friendly failure messages (failure_messages=1).
Audience and scenarios: targets enterprises and teams, offers multiple deployment options (audience_and_scenarios=2). Capability boundaries: clearly distinguishes community and paid features (capability_boundaries=2). Trigger precision: automations support record changes, schedules, and webhooks, but no detailed trigger conditions (trigger_precision=2). Environment fit: supports cloud and self-hosted, provides Docker deployment (environment_fit=2).
Information architecture: README well-structured with quick guide and feature list (information_architecture=2). Install notes: development steps provided, but production deployment relies on external docs (install_notes=2). Naming stability: version numbers clear, but no API stability guarantee (naming_stability=1). Examples and FAQ: examples and links provided, but no FAQ (examples_and_faq=2). Known limitations: no explicit list (known_limitations=1). License: AGPL-3.0 and MIT clearly stated, but metadata says NOASSERTION (license=2). Versioning and changelog: version number present, but no changelog file (versioning_changelog=1). Maintenance responsibility: security policy and community links, but no explicit maintainers (maintenance_responsibility=1).
Output usability: API and UI provided, output formats clear (output_usability=2). Marginal value: AI features offered, but no comparison with other tools (marginal_value=2). Cost-benefit: free community edition, but paid features' costs unclear (cost_benefit=2).
Claim traceability: README features supported by code and tests, but no specific evidence links (claim_traceability=1). Cross-source corroboration: tests and CI exist, but no independent verification (cross_source_corroboration=1). Fact-inference separation: README distinguishes facts and vision, but not explicitly labeled (fact_inference_separation=1).
- Publisher identity unverified; be cautious about supply chain risks.
- Dependency security lacks vulnerability scanning evidence; consider checking dependency versions.
- AI features may make external calls; clarify data flow and permission controls.
- No known limitations or changelog provided, affecting user assessment.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Feature Updates - Added an official MCP server for connecting Claude Code, Codex, Cursor, and other compatible AI clients to Teable through guided OAuth authorization, without manually creating a personal access token. Self-hosted instances support connections at <site-url>/mcp without additional configuration. - Connected AI clients can list projects, inspect tables and fields, query and manage records, and discover APIs for advanced operations, all within the user’s existing permissions. …View on GitHub ↗ -
Release notes excerpt
Feature Updates - Added This Year, Last Year, and Next Year presets to date filters. - Added “Add to chat” to the record detail menu, with correct context for records opened from linked tables or outside the current filtered view. On mobile, the action opens AI chat and reliably adds the record. - Skill activation now appears as a dedicated step in web and mobile chats, showing the skill name, description, and expandable instructions. Messages starting with /skill-name now reliably activate available skills. …View on GitHub ↗ -
Release notes excerpt
Feature Updates - Editors can now import CSV files and append data to existing tables without owner-level permissions. Imported records identify the importing editor as their creator. - Added reusable structured queries with field selection, aliases, filters, sorting, pagination, and aggregations, available through a unified API endpoint and CLI. - Added a versioned Query Library with stable query IDs, immutable revisions, pinned or latest-version references, sharing controls, revision restoration, and protection against conflicting updates. Bug Fixes & Improvements …View on GitHub ↗