AI Agents
system-prompts-and-models-of-ai-tools
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Q…
★ 144.0k starsGPL-3.0
View guide →// agents · stanfordnlp/dspy
dspy
dspy is an open-source ai agents project by stanfordnlp (stanfordnlp/dspy on GitHub). It has 38,554 GitHub stars and 3,406 forks, is released under the MIT license, and was last updated on GitHub on 7 October 2026.
Program language models with code and compilers — not fragile prompts.
★ 38.6k stars⑂ 3.4k forksMITupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- stanfordnlp/dspy
- GitHub stars
- 38,554
- Forks
- 3,406
- License
- MIT
- Last updated on GitHub
- 7 October 2026
- Category
- AI Agents
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Pick a use case
Choose one concrete task — narrow beats ambitious for a first run.
- Clone and explore
Fetch the source and skim the docs folder.
- Configure credentials
Set the environment variables or keys the project needs.
- Launch your first run
Execute the example workflow and watch what happens.
// features
Why people love it
Program, don't prompt
LM behavior as code with signatures.
Automatic optimizers
Compile and tune programs with data.
Multi-model support
Not tied to a single provider.
Composable modules
Build complex pipelines from simple parts.
Evaluation built in
Measure what your tuning actually did.
Research pedigree
From Stanford NLP, with papers behind it.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/stanfordnlp/dspy.git cd dspy - Step 2 — Create a venv and install
Isolate dependencies, then install requirements.
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt - Step 3 — Run it
Launch using the entry point shown in the README.
python -m dspy # check README for the exact command
// use cases
What you can build
- Optimize a RAG pipeline systematically.
- Build LM features with versioned, testable code.
- Tune few-shot examples automatically.
- Compare model behavior across tasks.
Advertisement
// faq
Questions, answered
Who maintains dspy?
It is an open-source project at stanfordnlp/dspy with 3406 forks. Check the contributors tab and recent commits to judge how active maintenance is.
Is dspy free to use?
Yes — it's MIT licensed: free to use, modify, and ship commercially. Just keep the license notice in copies.
Do I need ML expertise?
Some — DSPy is a programming framework with optimizers, aimed at engineers comfortable with data-driven iteration.
Which models does it support?
Many major providers; programs are model-agnostic by design. Check the docs for the current list.
How do I get started?
Clone the repo and follow the README quickstart — the docs at https://dspy.ai walk through setup.
// keep exploring
Similar tools
AI Agents
openpi
Physical Intelligence's open vision-language-action models (pi0, pi0-FAST, pi0.5) for robot policies.
★ 14.1k starsApache-2.0
View guide →Agents
magentic
Use LLMs as plain Python functions: prompts become typed, testable code.
★ 2.4k starsMIT
View guide →AI Agents
unstructured
Turn messy documents into clean, structured data for language models.
★ 15.5k starsApache-2.0
View guide →AI Agents
ida-pro-mcp
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
★ 12.5k starsMIT
View guide →AI Agents
lerobot
Hugging Face's LeRobot: datasets, models and tools to make real-world robotics AI accessible
★ 28.0k starsApache-2.0
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if dspy is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to dspy — keep exploring the shelf either side of it.
- UI-TARS-desktop★ 39.2k
ByteDance's open-source multimodal AI agent stack: GUI agents that see and operate real desktops
- playwright-mcp★ 37.9k
Microsoft's Playwright-powered MCP server for browser automation.
- OpenViking★ 39.4k
A self-evolving context database unifying agent memory, RAG, and skills.
- khoj★ 37.6k
Your self-hostable AI second brain for answers, agents, and automations.
- LightRAG★ 40.0k
Simple, fast retrieval-augmented generation with graph smarts.
- firecracker★ 37.2k
Secure, fast microVMs that make serverless possible.
Get dspy
Free and open — grab the source, star the repo, and start creating.