Overview
Research summary
DSPy is an MIT-licensed Python framework for programming and optimizing language-model systems rather than hand-authoring every prompt. Developers define composable modules and typed signatures in ordinary code, connect models, retrievers or tools, and then use DSPy optimizers to improve instructions, demonstrations or model weights against an application-specific metric. The same programming model can be used for simple prediction components, RAG pipelines and agent loops such as ReAct.
This makes DSPy different from orchestration frameworks whose primary job is routing execution between agents: its distinctive layer is systematic optimization of the model-facing program itself. DSPy can still participate inside a larger workflow or agent platform, while model providers and retrieval systems remain replaceable dependencies. The main repository is Python and MIT licensed; model APIs, datasets and evaluation infrastructure used by an application retain their own terms.
Repository summary
- Stars
- 38,066
- Open issues
- Unavailable
- Last push
- 2026-09-16
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Version
- Unavailable
Recorded catalogue figures. View repository data and provenance →
Classification
Pricing & services
Paid services unknown
Whether the provider offers paid products or services has not been established.
Licence scope
Implementation
Recorded implementation details and interfaces for DSPy.
Implementation details
Python declarative and optimizing LM programming framework
- Languages
- Python
- Repository type
- source
Recorded interfaces and capabilities
Licence scope
Repository
Repository snapshots, release information and recorded maintenance signals.
Repository snapshot
- Stars
- 38,066
- Open issues
- Unavailable
- Last push
- 2026-09-16
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Archived
- Not recorded
Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).
Maintenance and provenance
- Catalogue snapshot
- 2026-10-06
- Stars source
- Recorded fallback
- Last push source
- Recorded fallback
Documentation
Recorded references and research provenance for this entry.
Recorded sources 6
- https://dspy.ai Project page · Research reference
- https://github.com/stanfordnlp/dspy Linked repository · Research reference
- https://github.com/stanfordnlp/dspy/blob/main/README.md Research reference
- https://raw.githubusercontent.com/stanfordnlp/dspy/HEAD/README.md Research reference
- https://discord.com/api/v10/invites/XCGy2WDCQB?with_counts=false&with_expiration=true Research reference
- https://api.github.com/repos/stanfordnlp/dspy Research reference
Research metadata
- Research date
- 2026-09-16
- Catalogue snapshot
- 2026-10-06
Community & social 3 channels
Communities
- Discorddiscord.gg/XCGy2WDCQBOfficial
Link details for Discord
- Access
- Public
- Last checked
- GitHub Discussionsgithub.com/stanfordnlp/dspy/discussionsOfficialDiscussion
Link details for GitHub Discussions
- Access
- Public
- Last checked
Social & updates
- Xx.com/DSPyOSSOfficial
Link details for X
- Last checked