Just releases DSPy support for Jev, complete with an optimizer. Really excited to start building modular systems with this: www.cmpnd.ai/blog/buildin...
Building & Optimizing Jev Programs with DSPy — Cmpnd
Many DSPy Signatures already define decisions. Today, they can run on System One models.
www.cmpnd.ai
September 25, 2026 at 1:12 PM
Just releases DSPy support for Jev, complete with an optimizer. Really excited to start building modular systems with this: www.cmpnd.ai/blog/buildin...
I finally tried DSPy and now I get why everyone won't shut up about it by Pedram Navid
pedramnavid.com/blog/dspy-pa...
pedramnavid.com/blog/dspy-pa...
Pedram Navid | I finally tried DSPy and now I get why everyone won't shut up about it
DSPy is my new favorite tool for building LLM applications, and it should be yours too
pedramnavid.com
August 24, 2025 at 1:16 PM
I finally tried DSPy and now I get why everyone won't shut up about it by Pedram Navid
pedramnavid.com/blog/dspy-pa...
pedramnavid.com/blog/dspy-pa...
If you've been trying to figure out DSPy - the automatic prompt optimization system - this talk by @dbreunig.bsky.social is the clearest explanation I've seen yet, with a very useful real-world case study www.youtube.com/watch?v=I9Zt...
My notes here: simonwillison.net/2025/Oct/4/d...
My notes here: simonwillison.net/2025/Oct/4/d...
Let the LLM Write the Prompts: An Intro to DSPy in Compound AI Pipelines
YouTube video by Databricks
www.youtube.com
October 4, 2025 at 11:05 PM
If you've been trying to figure out DSPy - the automatic prompt optimization system - this talk by @dbreunig.bsky.social is the clearest explanation I've seen yet, with a very useful real-world case study www.youtube.com/watch?v=I9Zt...
My notes here: simonwillison.net/2025/Oct/4/d...
My notes here: simonwillison.net/2025/Oct/4/d...
While at Nvidia, they're warning people that programming as a skill is going to become useless because of AI, others are going back to programming
github.com/stanfordnlp/...
github.com/stanfordnlp/...
GitHub - stanfordnlp/dspy: DSPy: The framework for programming—not prompting—foundation models
DSPy: The framework for programming—not prompting—foundation models - stanfordnlp/dspy
github.com
February 28, 2024 at 8:01 AM
While at Nvidia, they're warning people that programming as a skill is going to become useless because of AI, others are going back to programming
github.com/stanfordnlp/...
github.com/stanfordnlp/...
i feel like DSPy is beginning to occupy the Haskell tier
everyone: "DSPy is great, all LLM programming should be done like this"
narrator: "No real LLM programming is done this way"
everyone: "DSPy is great, all LLM programming should be done like this"
narrator: "No real LLM programming is done this way"
October 6, 2025 at 2:12 PM
i feel like DSPy is beginning to occupy the Haskell tier
everyone: "DSPy is great, all LLM programming should be done like this"
narrator: "No real LLM programming is done this way"
everyone: "DSPy is great, all LLM programming should be done like this"
narrator: "No real LLM programming is done this way"
📦 stanfordnlp / dspy
⭐ 1,963 (+77)
🗒 Jupyter Notebook
DSPy: The framework for programming with foundation models
⭐ 1,963 (+77)
🗒 Jupyter Notebook
DSPy: The framework for programming with foundation models
GitHub - stanfordnlp/dspy: DSPy: The framework for programming with foundation models
DSPy: The framework for programming with foundation models - GitHub - stanfordnlp/dspy: DSPy: The framework for programming with foundation models
github.com
August 31, 2023 at 2:50 PM
📦 stanfordnlp / dspy
⭐ 1,963 (+77)
🗒 Jupyter Notebook
DSPy: The framework for programming with foundation models
⭐ 1,963 (+77)
🗒 Jupyter Notebook
DSPy: The framework for programming with foundation models
Using DSPy to categorize historic events with Llamas www.dbreunig.com/2024/12/12/p...
Pipelines & Prompt Optimization with DSPy
Writing about technology, culture, media, data, and all the ways they interact.
www.dbreunig.com
December 13, 2024 at 6:45 AM
Using DSPy to categorize historic events with Llamas www.dbreunig.com/2024/12/12/p...
📦 stanfordnlp / dspy
⭐ 19,527 (+35)
🗒 Python
DSPy: The framework for programming—not prompting—language models
⭐ 19,527 (+35)
🗒 Python
DSPy: The framework for programming—not prompting—language models
GitHub - stanfordnlp/dspy: DSPy: The framework for programming—not prompting—language models
DSPy: The framework for programming—not prompting—language models - stanfordnlp/dspy
github.com
December 5, 2024 at 6:01 PM
📦 stanfordnlp / dspy
⭐ 19,527 (+35)
🗒 Python
DSPy: The framework for programming—not prompting—language models
⭐ 19,527 (+35)
🗒 Python
DSPy: The framework for programming—not prompting—language models
You know how language models have this cloying, reassuring, explanatory style?
Only until you push them! If you ask them a sufficiently hard question they come at you like a spider monkey who ate a textbook, a thesaurus, and a lot of cocaine.
Only until you push them! If you ask them a sufficiently hard question they come at you like a spider monkey who ate a textbook, a thesaurus, and a lot of cocaine.
August 24, 2025 at 9:07 PM
You know how language models have this cloying, reassuring, explanatory style?
Only until you push them! If you ask them a sufficiently hard question they come at you like a spider monkey who ate a textbook, a thesaurus, and a lot of cocaine.
Only until you push them! If you ask them a sufficiently hard question they come at you like a spider monkey who ate a textbook, a thesaurus, and a lot of cocaine.
GEPA: prompt optimization can exceed RL performance
They used Qwen3-8B (which was not trained for math, coding, agency, etc.) and show that GEPA performed better than RL rollouts
paper: arxiv.org/abs/2507.19457
github: github.com/gepa-ai/gepa
DSPy docs: dspy.ai/api/optimize...
They used Qwen3-8B (which was not trained for math, coding, agency, etc.) and show that GEPA performed better than RL rollouts
paper: arxiv.org/abs/2507.19457
github: github.com/gepa-ai/gepa
DSPy docs: dspy.ai/api/optimize...
1. GEPA Overview - DSPy
The framework for programming—rather than prompting—language models.
dspy.ai
October 22, 2025 at 11:55 AM
GEPA: prompt optimization can exceed RL performance
They used Qwen3-8B (which was not trained for math, coding, agency, etc.) and show that GEPA performed better than RL rollouts
paper: arxiv.org/abs/2507.19457
github: github.com/gepa-ai/gepa
DSPy docs: dspy.ai/api/optimize...
They used Qwen3-8B (which was not trained for math, coding, agency, etc.) and show that GEPA performed better than RL rollouts
paper: arxiv.org/abs/2507.19457
github: github.com/gepa-ai/gepa
DSPy docs: dspy.ai/api/optimize...
🟠 DSPy 3.3.0b1 adds native tool-calling ReActV2 and a typed LM boundary
Stanford NLP shipped DSPy 3.3.0b1 with a new ReActV2 agent module built around native tool calling, plus a new typed, provider-neutral LM...
https://github.com/stanfordnlp/dspy/releases/tag/3.3.0b1
#AI #AgentWyre
Stanford NLP shipped DSPy 3.3.0b1 with a new ReActV2 agent module built around native tool calling, plus a new typed, provider-neutral LM...
https://github.com/stanfordnlp/dspy/releases/tag/3.3.0b1
#AI #AgentWyre
Release 3.3.0b1 · stanfordnlp/dspy · GitHub
DSPy: The framework for programming—not prompting—language models - Release 3.3.0b1 · stanfordnlp/dspy
github.com
May 28, 2026 at 3:03 AM
🟠 DSPy 3.3.0b1 adds native tool-calling ReActV2 and a typed LM boundary
Stanford NLP shipped DSPy 3.3.0b1 with a new ReActV2 agent module built around native tool calling, plus a new typed, provider-neutral LM...
https://github.com/stanfordnlp/dspy/releases/tag/3.3.0b1
#AI #AgentWyre
Stanford NLP shipped DSPy 3.3.0b1 with a new ReActV2 agent module built around native tool calling, plus a new typed, provider-neutral LM...
https://github.com/stanfordnlp/dspy/releases/tag/3.3.0b1
#AI #AgentWyre
Dspy + Gradio + Huggingface = Magic !!
December 4, 2024 at 5:16 PM
Dspy + Gradio + Huggingface = Magic !!
did you hear what he said about DSPy?? get him!! 😅
No, it's a good idea! We just need something better than DSPy to do the initial variation, I guess.
October 9, 2025 at 5:39 PM
did you hear what he said about DSPy?? get him!! 😅
DSRs — DSPy for Rust
it looks pretty complete. i’m fairly anti-framework, but DSPy actually does provide solid abstractions. this is good
github.com/krypticmouse...
it looks pretty complete. i’m fairly anti-framework, but DSPy actually does provide solid abstractions. this is good
github.com/krypticmouse...
GitHub - krypticmouse/DSRs: A DSPy rewrite to(not port) Rust
A DSPy rewrite to(not port) Rust. Contribute to krypticmouse/DSRs development by creating an account on GitHub.
github.com
September 10, 2025 at 5:44 PM
DSRs — DSPy for Rust
it looks pretty complete. i’m fairly anti-framework, but DSPy actually does provide solid abstractions. this is good
github.com/krypticmouse...
it looks pretty complete. i’m fairly anti-framework, but DSPy actually does provide solid abstractions. this is good
github.com/krypticmouse...
DSPy requires more upfront learning than just writing natural language prompts. But once you get it, it makes building, maintaining, & improving AI programs so much easier.
We aim to soften the learning curve to make the benefits more accessible, starting with more new docs and front page. dspy.ai
We aim to soften the learning curve to make the benefits more accessible, starting with more new docs and front page. dspy.ai
DSPy
The framework for programming—rather than prompting—language models.
dspy.ai
May 29, 2026 at 2:49 AM
DSPy requires more upfront learning than just writing natural language prompts. But once you get it, it makes building, maintaining, & improving AI programs so much easier.
We aim to soften the learning curve to make the benefits more accessible, starting with more new docs and front page. dspy.ai
We aim to soften the learning curve to make the benefits more accessible, starting with more new docs and front page. dspy.ai
DSPy : un framework Open Source développé par Stanford NLP pour concevoir des systèmes d'IA modulaires en programmant les modèles de langage plutôt qu'en les sollicitant via des prompts.
👉 Le projet : github.com/stanfordn...
👉 Le projet : github.com/stanfordn...
June 6, 2025 at 7:30 PM
DSPy : un framework Open Source développé par Stanford NLP pour concevoir des systèmes d'IA modulaires en programmant les modèles de langage plutôt qu'en les sollicitant via des prompts.
👉 Le projet : github.com/stanfordn...
👉 Le projet : github.com/stanfordn...
No, it's a good idea! We just need something better than DSPy to do the initial variation, I guess.
October 9, 2025 at 5:32 PM
No, it's a good idea! We just need something better than DSPy to do the initial variation, I guess.
Also the goal of DSpy
July 16, 2025 at 7:50 PM
Also the goal of DSpy
they improved Claude Code by 5% using only 150(!!) examples
unlike some DSPy algorithms, this modifies the English, not just examples
unlike some DSPy algorithms, this modifies the English, not just examples
November 21, 2025 at 9:28 PM
they improved Claude Code by 5% using only 150(!!) examples
unlike some DSPy algorithms, this modifies the English, not just examples
unlike some DSPy algorithms, this modifies the English, not just examples
This was built by a long-time DSPy community member!
March 4, 2025 at 12:34 AM
This was built by a long-time DSPy community member!
if someone downplays or disses DSPy, it’s worth considering that they just have poor data hygiene
May 6, 2025 at 11:01 PM
if someone downplays or disses DSPy, it’s worth considering that they just have poor data hygiene
THE LLM WORLD ISN’T JUST CHATGPT ANYMORE.
It’s an entire ecosystem.
Think of it like a tech stack:
→ Models
GPT
Claude
Gemini
Llama
→ Frameworks
LangChain
LlamaIndex
DSPy
→ Tools
MCP
Vector databases
Web search
Code execution
→ Applications
AI agents
Coding assistants
It’s an entire ecosystem.
Think of it like a tech stack:
→ Models
GPT
Claude
Gemini
Llama
→ Frameworks
LangChain
LlamaIndex
DSPy
→ Tools
MCP
Vector databases
Web search
Code execution
→ Applications
AI agents
Coding assistants
September 27, 2026 at 4:44 AM
THE LLM WORLD ISN’T JUST CHATGPT ANYMORE.
It’s an entire ecosystem.
Think of it like a tech stack:
→ Models
GPT
Claude
Gemini
Llama
→ Frameworks
LangChain
LlamaIndex
DSPy
→ Tools
MCP
Vector databases
Web search
Code execution
→ Applications
AI agents
Coding assistants
It’s an entire ecosystem.
Think of it like a tech stack:
→ Models
GPT
Claude
Gemini
Llama
→ Frameworks
LangChain
LlamaIndex
DSPy
→ Tools
MCP
Vector databases
Web search
Code execution
→ Applications
AI agents
Coding assistants
Finally getting a handle on #DSPy for simple use-cases! I've even built out a module or two.
Built this today to understand better how a few of the optimizers work under the hood:
github.com/BenMcH/DSPy-...
Built this today to understand better how a few of the optimizers work under the hood:
github.com/BenMcH/DSPy-...
DSPy-Experiments/dspy.ipynb at main · BenMcH/DSPy-Experiments
Contribute to BenMcH/DSPy-Experiments development by creating an account on GitHub.
github.com
April 6, 2025 at 7:18 PM
Finally getting a handle on #DSPy for simple use-cases! I've even built out a module or two.
Built this today to understand better how a few of the optimizers work under the hood:
github.com/BenMcH/DSPy-...
Built this today to understand better how a few of the optimizers work under the hood:
github.com/BenMcH/DSPy-...