{"full_name":"stanfordnlp/dspy","owner":"stanfordnlp","name":"dspy","shard":"1","url":"https://github.com/stanfordnlp/dspy","description":"DSPy: The framework for programming—not prompting—language models","homepage":"https://dspy.ai","topics":[],"tag_pages":[],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/3046006?v=4","created_at":"2023-01-09T21:01:51Z","pushed_at":"2026-11-13T14:13:09Z","metrics":{"stars":39078,"forks":3517,"watchers":209,"issues":1758,"prs":3296,"releases":115,"issues_open":344,"issues_closed":1414,"prs_open":439,"prs_closed":925,"prs_merged":1932,"discussions":98},"growth":{"day":{"stars":25,"forks":1,"base_day":"2026-11-15"},"week":{"stars":97,"forks":24,"base_day":"2026-11-09"},"month":{"stars":496,"forks":109,"base_day":"2026-10-17"}},"history":{"dates":["2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[37654,37709,37729,37753,37774,37791,37833,37858,37882,37900,37948,37984,38011,38043,38070,38100,38120,38146,38183,38211,38233,38259,38282,38341,38401,38422,38454,38470,38487,38507,38520,38546,38558,38566,38582,38601,38612,38638,38661,38669,38697,38705,38720,38736,38755,38769,38803,38820,38832,38847,38857,38889,38904,38981,38991,39011,39020,39025,39032,39053,39078],"forks":[3271,3279,3281,3284,3285,3289,3291,3294,3297,3305,3307,3310,3316,3317,3318,3323,3322,3326,3337,3344,3351,3353,3357,3365,3374,3379,3385,3390,3395,3398,3402,3405,3406,3407,3408,3415,3419,3423,3429,3431,3437,3438,3441,3444,3447,3453,3456,3456,3457,3458,3462,3476,3480,3493,3496,3504,3506,3508,3510,3516,3517],"watchers":[210,213,213,213,213,213,215,215,215,215,215,215,215,215,216,216,216,218,219,219,219,219,220,219,220,219,219,217,217,217,218,218,218,218,218,218,218,218,218,218,217,217,217,217,217,212,211,210,210,209,209,209,209,209,209,209,209,209,209,209,209],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,343,344,344,344,344,344],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,434,436,437,437,437,439]},"boards":{},"same_owner":[{"full_name":"stanfordnlp/stanza","name":"stanza","shard":"1","boards":{}}],"issues":[{"number":1539,"title":"ValueError: Expected dict_keys(['answer']) but got dict_keys([])","comments":35,"created_at":"2024-09-25T12:21:03Z"},{"number":1719,"title":"How do I load huggingface models?","comments":20,"created_at":"2024-10-29T23:12:57Z"},{"number":1570,"title":"Use of LiteLLM Router for load balancing and fallbacks","comments":19,"created_at":"2024-10-01T17:48:11Z"},{"number":9034,"title":"[Feature] Coding agent CLIs with DSPy - a client that proxies DSPy calls through arbitrary CLI commands","comments":16,"created_at":"2025-11-08T15:18:19Z"},{"number":8946,"title":"[Bug] ColBERT is down","comments":16,"created_at":"2025-10-15T16:26:33Z"},{"number":8067,"title":"[Bug] Ollama requests fail when including an Image","comments":13,"created_at":"2025-04-13T17:43:24Z"},{"number":9097,"title":"[Feature] Maybe we need DSPy Cookbook?","comments":11,"created_at":"2025-11-28T03:08:02Z"},{"number":7830,"title":"[Feature] Print the final prompt of a DSPy program","comments":11,"created_at":"2025-02-20T22:42:57Z"}],"discussions":[{"number":10881,"title":"Chopper: a small open model that cuts only the needed sentences out of retrieved text","comments":0,"category":"Show and tell","created_at":"2026-11-14T09:12:29Z"},{"number":10875,"title":"mcp-slim: Zero-dependency MCP stdio proxy to cut DSPy ReAct tool schema & output tokens by 50%-98%","comments":0,"category":"Show and tell","created_at":"2026-11-12T02:35:31Z"},{"number":10866,"title":"3.5.0","comments":0,"category":"Announcements","created_at":"2026-11-10T16:25:48Z"},{"number":10734,"title":"Can We \"Train\" MCP Tools and Agent Skills Through Expert Demonstrations and Iterative Feedback?","comments":0,"category":"Ideas","created_at":"2026-10-28T09:04:33Z"},{"number":10507,"title":"Optimisers absorb format non-compliance and the cost is invisible in the final score","comments":0,"category":"General","created_at":"2026-09-26T02:28:08Z"},{"number":10450,"title":"Proposal: Latent Space (Vector) Communication Protocol for Multi-Agent & Intra-Model Systems","comments":1,"category":"Ideas","created_at":"2026-09-18T09:21:55Z"},{"number":10439,"title":"Show and Tell: A package with `StructuredOutputAdapter` for getting better structured output from smaller models","comments":2,"category":"Show and tell","created_at":"2026-09-17T06:54:49Z"},{"number":10394,"title":"Show and Tell: Zero-Daemon Crash Recovery for Long-Running DSPy Optimizers (MIPROv2 / Teleprompters)","comments":0,"category":"Show and tell","created_at":"2026-09-13T18:59:54Z"}],"latest_release":{"name":"3.5.0","tag":"3.5.0","published_at":"2026-11-10T16:25:47Z","body":"# DSPy 3.5: A Lighter, Faster Foundation\r\n\r\nDSPy 3.5 brings a lighter LM layer, graduated core modules, and new History and image capabilities for RLM.\r\n\r\n## Upgrading from 3.4.1\r\n\r\n**This release changes prompts, defaults and APIs.** Read the [upgrade guide](https://dspy.ai/current/community/upgrading-to-3-5/) for breaking changes, migration steps and compatibility limits, and re-evaluate optimized programs.\r\n\r\n## Highlights\r\n\r\n### RLM, Flex and GEPA graduate\r\n\r\n`dspy.RLM`, `dspy.Flex` and `dspy.GEPA` are no longer experimental.\r\n\r\n### ReActV2 now replaces ReAct\r\n\r\nReActV2 is now simply `dspy.ReAct`, with structured History and a typed `submit` tool; the old name is deprecated until 3.6.\r\n\r\n### Rich tool results\r\n\r\nTools can return images, files and other DSPy content parts on supported provider routes.\r\n\r\n### RLM History — authored by Matt Mannucci (@mannuch)\r\n\r\nRLM can save and reload conversation History for later calls; it does not restore live interpreter variables.\r\n\r\n### A lighter LM foundation — lm15 work by Maxime Rivest (@MaximeRivest), integration by Isaac Miller (@isaacbmiller)\r\n\r\nLiteLLM and OpenAI’s Python library are now optional: DSPy calls supported providers through the lightweight lm15 engine.\r\n\r\n| Measured default install | 3.3.0 | 3.5 development snapshot |\r\n| --- | --- | --- |\r\n| Installed package files, including bytecode | 206.7 MiB | 30.9 MiB |\r\n| Dependencies, excluding DSPy | 65 | 25 |\r\n| Fresh-process import, best of ten | 1.01 s | 0.49 s |\r\n\r\n### Automatic API-family routing\r\n\r\n`model_type=\"auto\"` is the default, rather than explicitly selecting chat or responses.\r\n\r\n### XMLAdapter is now the default Adapter\r\n\r\nXMLAdapter now formats and parses predictor calls by default, changing prompts and the output contract even when your Signature stays the same.\r\n\r\n### Native reasoning and explicit plans\r\n\r\nPrefer native reasoning; request an explicit plan when planning before acting helps the task or it needs a human-auditable plan.\r\n\r\n### Disk caches: secure by default\r\n\r\nRestricted loading is now the default, and plain NumPy arrays are stored without pickle.\r\n\r\n### Image-capable RLM\r\n\r\nRLM can crop images with Pillow and send mixed text/image subqueries from its Python REPL.\r\n\r\nWith DSPy imported, an image-capable LM configured and the default Deno runtime available:\r\n\r\n```python\r\nrlm = dspy.RLM(\"photo: dspy.Image, question: str -> answer: str\")\r\nresult = rlm(photo=dspy.Image.from_path(\"photo.png\"), question=\"What is written on the smallest sign?\")\r\nprint(result.answer)\r\n```\r\n\r\n**Prewarmed Interpreters**\r\n\r\nReal DSPy now runs inside RLM and Flex interpreters, with a precompiled standard library, cached startup snapshots and `InterpreterPool` for prewarming.\r\n\r\n| Measured path | 3.4.1 | 3.5 development snapshot |\r\n| --- | --- | --- |\r\n| Cached Deno startup + first execution | 1.59 s | 0.45 s |\r\n| DummyLM Flex forward | 1.61 s | 0.63 s |\r\n| Flex with a ready size-one pool | — | 0.10 s |\r\n\r\nMedians of nine fresh processes per path, with prepared runtime caches; pool readiness costs another 0.55 s, excluded from the pooled forward. First-use preparation can be slower.\r\n\r\n## Full PR List\r\n\r\nAll 99 PRs in the verified range appear once in the list below. Earlier intermediate bundled-lm15 and metadata updates are included for completeness; the cutoff contains bundled lm15 2.2.0 and metadata sourced from released LiteLLM 1.108.3.\r\n\r\n### Language Models, Adapters, and Reasoning\r\n\r\n- fix(xml): honor positional tuple schemas by @isaacbmiller ([#10850](https://github.com/stanfordnlp/dspy/pull/10850)).\r\n- fix(adapters): preserve nested XML enum and null guidance by @isaacbmiller ([#10859](https://github.com/stanfordnlp/dspy/pull/10859)).\r\n- Default LM API-family selection to native lm15 routing by @isaacbmiller ([#10856](https://github.com/stanfordnlp/dspy/pull/10856)).\r\n- fix: honor reasoning dictionaries in ChainOfThought by @isaacbmiller ([#10842](https://github.com/stanfordnlp/dspy/pull/10842)).\r\n- fix(xml): pars","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}