Skip to content

Commit 4f4844f

Browse files
anandgupta42claude
andauthored
docs: rewrite README for open-source launch (#33)
Overhaul the README to reflect the current state of the project and make it compelling for open-source discovery: - Update tool count from "40+" to "55+" (actual current count) - Remove reference to query cost prediction (feature was removed) - Add comparison table: general coding agents vs altimate-code - Add quick demo section with practical workflow examples - Add agent modes table (Builder, Analyst, Validator, Migrator, Executive) - Add /discover command to quick start flow - Feature 11 data engineering skills under dbt Native section - Add accuracy stats (100% on 1,077 queries, 100% edge match on 500) - Add banner image, docs badge, and doc page links - Add community section (Issues, Discussions, Security) - Update tagline to "The data engineering agent for dbt, SQL, and cloud warehouses" Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
1 parent c05720a commit 4f4844f

File tree

1 file changed

+102
-85
lines changed

1 file changed

+102
-85
lines changed

README.md

Lines changed: 102 additions & 85 deletions
Original file line numberDiff line numberDiff line change
@@ -1,104 +1,124 @@
11
<div align="center">
22

3+
<img src="docs/docs/assets/images/altimate-code-banner.png" alt="altimate-code" width="600" />
4+
35
# altimate-code
46

5-
**The AI coding agent for data teams.**
7+
**The data engineering agent for dbt, SQL, and cloud warehouses.**
68

7-
Batteries included for SQL, dbt, and data warehouses.
9+
An AI-powered CLI with 55+ specialized tools — SQL analysis, schema inspection,
10+
column-level lineage, FinOps, and PII detection. Connects to your warehouse,
11+
understands your data, and helps you ship faster.
812

913
[![npm](https://img.shields.io/npm/v/@altimateai/altimate-code)](https://www.npmjs.com/package/@altimateai/altimate-code)
1014
[![PyPI](https://img.shields.io/pypi/v/altimate-engine)](https://pypi.org/project/altimate-engine/)
1115
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](./LICENSE)
1216
[![CI](https://github.com/AltimateAI/altimate-code/actions/workflows/ci.yml/badge.svg)](https://github.com/AltimateAI/altimate-code/actions/workflows/ci.yml)
17+
[![Docs](https://img.shields.io/badge/docs-altimate--code.sh-blue)](https://altimate-code.sh)
1318

1419
</div>
1520

1621
---
1722

18-
An AI coding agent with 40+ specialized data tools, column-level lineage, dbt integration, and warehouse connectivity built in -- all available to any AI provider.
23+
## Why altimate-code?
1924

20-
## Install
25+
General-purpose coding agents can write SQL, but they don't *understand* it. They can't trace lineage, detect anti-patterns, check PII exposure, or optimize warehouse costs — because they don't have the tools.
26+
27+
altimate-code is a fork of [OpenCode](https://github.com/anomalyco/opencode) rebuilt for data teams. It gives any LLM access to 55+ specialized data engineering tools, 11 purpose-built skills, and direct warehouse connectivity — so the AI works with your actual schemas, not guesses.
28+
29+
## General agents vs altimate-code
30+
31+
| Capability | General coding agents | altimate-code |
32+
|---|---|---|
33+
| SQL anti-pattern detection | None | 19 rules with confidence scoring |
34+
| Column-level lineage | None | Automatic from SQL |
35+
| Schema-aware autocomplete | None | Indexes your warehouse metadata |
36+
| Cross-dialect translation | None | Snowflake, BigQuery, Databricks, Redshift |
37+
| FinOps analysis | None | Credit analysis, expensive queries, warehouse sizing |
38+
| PII detection | None | Automatic column scanning |
39+
| dbt integration | Basic file editing | Manifest parsing, test generation, model scaffolding |
40+
41+
## Quick demo
2142

2243
```bash
23-
# npm
24-
npm i -g @altimateai/altimate-code
44+
# Auto-detect your data stack (dbt projects, warehouse connections, installed tools)
45+
> /discover
2546

26-
# Homebrew
27-
brew install AltimateAI/tap/altimate-code
47+
# Analyze a query for anti-patterns and optimization opportunities
48+
> Analyze this query for issues: SELECT * FROM orders JOIN customers ON orders.id = customers.order_id
49+
50+
# Translate SQL across dialects
51+
> /sql-translate this Snowflake query to BigQuery: SELECT DATEADD(day, 7, current_date())
52+
53+
# Generate dbt tests for a model
54+
> /generate-tests for models/staging/stg_orders.sql
55+
56+
# Get a cost report for your Snowflake account
57+
> /cost-report
2858
```
2959
30-
Then run `altimate-code` to launch the interactive TUI, or `altimate-code run "your prompt"` for one-shot mode.
60+
## Key Features
3161
32-
## Highlights
62+
### SQL Anti-Pattern Detection
63+
19 rules with confidence scoring — catches SELECT *, cartesian joins, non-sargable predicates, correlated subqueries, and more. **100% accuracy** on 1,077 benchmark queries.
3364
34-
| Capability | Details |
35-
|---|---|
36-
| **SQL analysis** | 40+ tools -- lint, format, transpile, optimize, safety checks |
37-
| **Column-level lineage** | Trace data flow through complex SQL and dbt models |
38-
| **dbt integration** | Manifest parsing, profile management, `+` operator |
39-
| **Warehouse connectivity** | Snowflake, BigQuery, Redshift, Databricks, Postgres, DuckDB, MySQL, SQL Server |
40-
| **PII detection** | Classify sensitive columns, flag risky queries |
41-
| **Query cost prediction** | Estimate execution costs before running |
42-
| **FinOps** | Credit analysis, query history insights |
43-
| **AI providers** | 15+ providers -- Anthropic, OpenAI, Gemini, Bedrock, and more |
44-
| **TUI + headless** | Interactive terminal UI or `altimate-code serve` for CI/CD |
45-
| **MCP + LSP** | Model Context Protocol and Language Server Protocol support |
65+
### Column-Level Lineage
66+
Automatic lineage extraction from SQL. Trace any column back through joins, CTEs, and subqueries to its source. Works standalone or with dbt manifests for project-wide lineage. **100% edge match** on 500 benchmark queries.
4667
47-
## Features
68+
### FinOps & Cost Analysis
69+
Credit analysis, expensive query detection, warehouse right-sizing, unused resource cleanup, and RBAC auditing.
4870
49-
### SQL Analysis (40+ tools)
71+
### Cross-Dialect Translation
72+
Transpile SQL between Snowflake, BigQuery, Databricks, Redshift, PostgreSQL, MySQL, SQL Server, and DuckDB.
5073
51-
The AI has access to specialized SQL tools that go far beyond what a general coding agent can do:
74+
### PII Detection & Safety
75+
Automatic column scanning for PII across 15 categories with 30+ regex patterns. Safety checks and policy enforcement before query execution.
5276
53-
- **Lint & validate** -- Catch anti-patterns like implicit casts, NULL comparisons, unused CTEs
54-
- **Format** -- Consistent SQL formatting across your team
55-
- **Transpile** -- Convert between Snowflake, BigQuery, Postgres, T-SQL, MySQL, DuckDB
56-
- **Optimize** -- Get index suggestions, query rewrites, complexity reduction
57-
- **Safety checks** -- Detect breaking changes, SQL injection risks, schema violations
58-
- **Test generation** -- Auto-generate SQL tests for your models
59-
- **Equivalence checking** -- Verify two queries produce the same results
77+
### dbt Native
78+
Manifest parsing, test generation, model scaffolding, incremental model detection, and lineage-aware refactoring. 11 purpose-built skills including medallion patterns, yaml config generation, and dbt docs.
6079
61-
### Column-Level Lineage
80+
## Install
81+
82+
```bash
83+
# npm (recommended)
84+
npm install -g @altimateai/altimate-code
6285

63-
Trace data flow at the column level through complex SQL transformations. Works standalone or with dbt manifests for project-wide lineage across models.
86+
# Homebrew
87+
brew install AltimateAI/tap/altimate-code
88+
```
6489
65-
### dbt Integration
90+
Then:
6691
67-
- Parse `manifest.json` and `profiles.yml` natively
68-
- Column-level lineage across dbt models with `+` operator for upstream/downstream selection
69-
- Execute dbt commands (compile, run, test) directly from the agent
70-
- Profile management across environments
92+
```bash
93+
altimate-code # Launch the interactive TUI
94+
altimate-code /discover # Auto-detect your data stack and go
95+
```
7196
72-
### Warehouse Connectivity
97+
`/discover` auto-detects dbt projects, warehouse connections (from `~/.dbt/profiles.yml`, Docker, environment variables), and installed tools (dbt, sqlfluff, airflow, dagster, and more).
7398
74-
Connect directly to your data warehouse -- the AI can query schemas, run SQL, and analyze query history:
99+
## Agent Modes
75100
76-
- Snowflake (with IAM auth)
77-
- BigQuery (service account + ADC)
78-
- Redshift (with IAM auth)
79-
- Databricks
80-
- PostgreSQL
81-
- DuckDB
82-
- MySQL
83-
- SQL Server
84-
- SSH tunneling for secure connections
101+
Each agent has scoped permissions and purpose-built tools for its role.
85102
86-
### AI Providers
103+
| Agent | Role | Access |
104+
|---|---|---|
105+
| **Builder** | Create dbt models, SQL pipelines, and data transformations | Full read/write |
106+
| **Analyst** | Explore data, run SELECT queries, and generate insights | Read-only enforced |
107+
| **Validator** | Data quality checks, schema validation, test coverage analysis | Read + validate |
108+
| **Migrator** | Cross-warehouse SQL translation, schema migration, dialect conversion | Read/write for migrations |
109+
| **Executive** | Business-audience summaries — translates findings into revenue, cost, and compliance impact | Read-only |
87110
88-
Use any model you want. altimate-code supports 15+ providers via the Vercel AI SDK:
111+
## Supported Warehouses
89112
90-
Anthropic, OpenAI, Google Gemini, Google Vertex AI, Amazon Bedrock, Azure OpenAI, Mistral, Groq, DeepInfra, Cerebras, Cohere, Together AI, Perplexity, xAI, OpenRouter, GitHub Copilot, GitLab
113+
Snowflake · BigQuery · Databricks · PostgreSQL · Redshift · DuckDB · MySQL · SQL Server
91114
92-
### And more
115+
First-class support with schema indexing, query execution, and metadata introspection. SSH tunneling available for secure connections.
93116
94-
- Interactive TUI with Solid.js + OpenTUI
95-
- Headless server mode (`altimate-code serve`)
96-
- MCP server support (stdio, HTTP, SSE transports)
97-
- LSP integration (workspace symbols, diagnostics)
98-
- Session management (continue, fork, export/import)
99-
- Custom agents and plugins
100-
- GitHub integration (PR analysis, automated workflows)
101-
- Token usage stats and cost tracking
117+
## Works with Any LLM
118+
119+
Model-agnostic — bring your own provider or run locally.
120+
121+
Anthropic · OpenAI · Google Gemini · Google Vertex AI · Amazon Bedrock · Azure OpenAI · Mistral · Groq · DeepInfra · Cerebras · Cohere · Together AI · Perplexity · xAI · OpenRouter · Ollama · GitHub Copilot
102122
103123
## Architecture
104124
@@ -115,25 +135,6 @@ The CLI handles AI interactions, TUI, and tool orchestration. The Python engine
115135
116136
**Zero-dependency bootstrap**: On first run the CLI downloads [`uv`](https://github.com/astral-sh/uv), creates an isolated Python environment, and installs the engine automatically. No system Python required.
117137
118-
## Development
119-
120-
See [CONTRIBUTING.md](./CONTRIBUTING.md) for the full setup guide.
121-
122-
```bash
123-
git clone https://github.com/AltimateAI/altimate-code.git
124-
cd altimate-code
125-
126-
# TypeScript
127-
bun install
128-
cd packages/altimate-code && bun test
129-
130-
# Python engine
131-
cd packages/altimate-engine
132-
python -m venv .venv && source .venv/bin/activate
133-
pip install -e ".[dev]"
134-
pytest
135-
```
136-
137138
### Monorepo structure
138139
139140
```
@@ -147,16 +148,32 @@ packages/
147148
148149
## Documentation
149150
150-
Full docs at [altimate-code.sh](https://altimate-code.sh).
151+
Full docs at **[altimate-code.sh](https://altimate-code.sh)**.
152+
153+
- [Getting Started](https://altimate-code.sh/getting-started/)
154+
- [SQL Tools](https://altimate-code.sh/data-engineering/tools/sql-tools/)
155+
- [Agent Modes](https://altimate-code.sh/data-engineering/agent-modes/)
156+
- [Configuration](https://altimate-code.sh/configure/model-providers/)
151157
152-
## Contributing
158+
## Community & Contributing
159+
160+
- **Issues**: [GitHub Issues](https://github.com/AltimateAI/altimate-code/issues)
161+
- **Discussions**: [GitHub Discussions](https://github.com/AltimateAI/altimate-code/discussions)
162+
- **Security**: See [SECURITY.md](./SECURITY.md)
153163
154164
Contributions welcome! Please read the [Contributing Guide](./CONTRIBUTING.md) before opening a PR.
155165
166+
```bash
167+
git clone https://github.com/AltimateAI/altimate-code.git
168+
cd altimate-code
169+
bun install
170+
cd packages/altimate-engine && python -m venv .venv && source .venv/bin/activate && pip install -e ".[dev]"
171+
```
172+
156173
## Acknowledgements
157174
158-
altimate-code is a fork of [opencode](https://github.com/anomalyco/opencode), the open-source AI coding agent. We build on top of their excellent foundation to add data-team-specific capabilities.
175+
altimate-code is a fork of [OpenCode](https://github.com/anomalyco/opencode), the open-source AI coding agent. We build on top of their excellent foundation to add data-team-specific capabilities.
159176
160177
## License
161178
162-
MIT -- see [LICENSE](./LICENSE).
179+
MIT see [LICENSE](./LICENSE).

0 commit comments

Comments
 (0)