The language built for data & ai

1. 01

   DATA IS A TYPE

   Tables, Streams, Tensors are native types in the language.

2. 02

   PIPELINES ARE PROGRAMS

   ETL/ELT flows are composable first-class constructs.

3. 03

   AI IS A VERB

   train, predict, embed, agent are keywords — not libraries.

4. 04

   PARALLEL BY DEFAULT

   No GIL, automatic partitioning across cores.

5. 05

   FAIL LOUD, RECOVER SMART

   Built-in error handling for unreliable data sources.

6. 06

   READABLE BEATS CLEVER

   Python-like readability, Rust-like safety guarantees.

7. 07

   FAST WITHOUT TRYING

   Compiled to native code with lazy evaluation. Performance is the default, not an afterthought.

Stop duct-taping together a dozen tools. TL unifies the modern data stack into one language.

No frameworks. No glue code. Define autonomous AI agents with tool-use, multi-provider LLM support, and lifecycle hooks — all with a single keyword.

1. 01

   First-Class Keyword

   agent is a language keyword, not a library import. Tools are TL functions wired directly to the LLM.

2. 02

   Any LLM Provider

   OpenAI, Anthropic, Ollama, or any OpenAI-compatible endpoint. Auto-detects protocol from model name. One base_url field to switch.

3. 03

   Automatic Tool Loop

   The runtime handles multi-turn tool calling, JSON arg conversion, and result formatting. You just write the function.

4. 04

   Lifecycle Hooks

   on_tool_call and on_complete blocks for logging, metrics, or custom logic at each step.

5. 05

   Pipeline Integration

   Agents use the same table, stream, and connectors as your data pipelines — no serialization layer needed.

6. 06

   Conversation Persistence

   run_agent(agent, message, history) maintains context across multi-turn sessions. No external memory store needed.

7. 07

   SSE Streaming

   stream_agent() delivers real-time token-by-token output via Server-Sent Events.

8. 08

   Retry & JSON Mode

   Automatic exponential backoff on 429/5xx errors. output_format: "json" for guaranteed structured output.

Model Context Protocol — the open standard that lets AI tools and data systems talk to each other. TL implements both sides: connect to any MCP server as a client, or expose TL functions to any AI tool as a server.

1. 01

   MCP Client

   mcp_connect() auto-detects stdio or HTTP transport. 10 builtins for tools, resources, prompts, and ping.

2. 02

   MCP Server

   mcp_serve() turns TL functions into MCP tools. Claude Desktop, Cursor, Windsurf can discover and call them.

3. 03

   Agent Integration

   mcp_servers: [...] in agent definitions. LLM sees one unified tool list — MCP and native tools dispatched transparently.

4. 04

   Sampling

   MCP servers can request LLM completions back through TL. Bidirectional AI communication over the protocol.

1. 01

   table<T>

   Columnar, lazy-evaluated, and partitionable. The core data type for batch processing.

   let users: table<User> = postgres("db").table("users")
2. 02

   stream<T>

   Infinite, windowed, real-time. For continuous data processing and event streams.

   stream process_events { from: kafka("events") window: tumbling(5m) }
3. 03

   tensor<dtype, shape>

   N-dimensional arrays for AI and machine learning. Shape-checked at compile time.

   let embeddings: tensor<float32, [256, 768]>
4. 04

   model

   A trained AI model as a first-class value. Serialize, version, deploy natively.

   model churn = train xgboost { ... }
5. 05

   agent

   Autonomous AI agent with tool-use, MCP server integration, and lifecycle hooks.

   agent bot { model: "gpt-4o", mcp_servers: [...], tools { ... } }

Rust-inspired ownership without lifetime annotations. The compiler guarantees memory safety and data-race freedom at compile time.

1. 01

   Every value has one owner

   let users = load("users.parquet") // `users` is the sole owner
2. 02

   Pipe |> moves ownership

   let active = users |> filter(age > 25) // `users` is now consumed
3. 03

   Clone or borrow for reuse

   let copy = users.clone() let ref = &users // read-only
4. 04

   Parallel partitions own data

   parallel for shard in users.partition(by: "region") // No locks needed — compiler guarantees it

Built entirely in Rust. TL-IR doubles as a query plan — enabling data-aware optimizations like predicate pushdown, column pruning, and join reordering.

TL's compiler sees the entire pipeline as one program — eliminating serialization boundaries between tools.

Targets based on architecture analysis. Benchmarks will be published with reproducible scripts.

Rust-inspired result<T, E> with data-specific error types and declarative cleaning — not try/catch bolted on as an afterthought.

First-class connectors for databases, object storage, message queues, and APIs. All type-safe and schema-aware.

20 connectors shipped — more coming with every release.

Bidirectional Python FFI via pyo3. Import Python modules, call functions, convert tensors to NumPy — all from TL code.

1. 01

   Bidirectional Conversion

   int, float, string, bool, list, map, set — all auto-converted between TL and Python.

2. 02

   Tensor ↔ NumPy

   TL tensors convert seamlessly to/from NumPy ndarrays for ML workflows.

3. 03

   Dot Notation Access

   Use natural math.sqrt(16) syntax on Python objects via method dispatch.

4. 04

   Feature-Gated

   Python FFI is opt-in via feature flag. Zero overhead when not used.

1. 01

   VS Code Extension & LSP

   Syntax highlighting, diagnostics, go-to-definition, hover docs, document symbols, rename refactoring, and find-references across files.

2. 02

   Package Manager

   tl add, tl update, tl outdated — full dependency management with lockfile and transitive resolution.

3. 03

   Formatter, Linter & Type Checker

   tl fmt, tl lint, tl check — AST-guided formatting, naming conventions, and compile-time type safety.

4. 04

   Doc Generation

   tl doc generates HTML, Markdown, or JSON docs from /// doc comments with cross-references.

5. 05

   Interactive Step Debugger

   tl debug — breakpoints, variable inspection, source listing, and stack traces. Debug pipelines interactively.

6. 06

   Data Inspection & Lineage

   tl inspect, tl profile, tl lineage — preview data, statistical profiles, and lineage graphs.

Rich standard library methods, native DateTime, window functions, and data engineering primitives — all built in.

"""..."""  Triple-quoted strings with automatic dedentation.

The only language where data pipelines, SQL-like queries, ML training, AI agents, MCP ecosystem, and real-time streaming are all first-class features — not libraries.