$
python
pandas
sql
spark
airflow
dbt
pytorch
langchain
churn
.tl
tl run
table<T>
columnar data
stream<T>
live events
tensor
ml math
model
trainable
agent
llm + tools
churn
.tl
|> pipe
customer
spend
c_8841
$24,180
c_2207
$19,540
c_5562
$17,905
c_0913
$15,300
pipe
moves
ownership · zero data races
parallel
by default · no GIL
compiles to
LLVM
native
Cranelift
JIT
WASM
in browser
CUDA
on GPU
0×
faster than Python
1B-row CSV
45s → <4s
0
tools replaced
churn
.tl
train + predict
train xgboost · gradient-boosted trees
AUC
0.00
churn
.tl
agent + mcp
mcp_connect
("github")
mcp_list_tools
()
mcp_call_tool
()
·
mcp_serve
() expose TL as MCP tools
client + server
tl.thinkingdbx.com
/app
Signed in
thinking
language
Pipelines
Agents
Notebooks
Connectors
TL Workspace
run · schedule · deploy
Pipeline
churn
.tl
Run
Deploy as HTTP endpoint
POST
tl.thinkingdbx.com/e/churn-score
Deploy
17+ connectors
notebooks
RBAC teams
audit log
thinking
language
The language built
for data & AI.
Pipelines, models, and agents. One language.
table
stream
tensor
model
agent
MCP-native
open source
· Apache 2.0 · cloud workspace
github.com/mplusm/thinkinglanguage ·
tl.thinkingdbx.com