deepfates/imp

declarative self-improving language-model programs for Elixir 😇

Language modelsElixir#beam#dspy#elixir#llm#machine-learning

5.3 Early signal Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of September 27, 2026, 23:23 UTC.

Open on Seismograph Open on GitHub

About the project

A port of DSPy to the BEAM: declarative LM programs in Elixir with signatures, optimizers and agents running as OTP processes.

Useful for

Declare a typed model call via a signature instead of writing prompts and parsers
Run GEPA optimization of a program against labeled examples and a metric
Start a ReAct agent with tools as a supervised process with call authorization

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

83 stars today. The usual pace is 0 per day, so that's 85× as much.
Before this, the repository barely got any stars — about 0 per day.
Hacker News: “Imp is a full port of DSPy to the BEAM” — 35 points, 3 h ago.
About 55 forks a day — people are taking the code.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 84
Today: 83
Forks: 6
Issues and pull requests: 234
Watchers: 0
Language: Elixir
License: MIT
Latest release: v0.5.0 · September 27, 2026
Created: July 10, 2026
Last push: September 27, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Hacker News discussions

Imp is a full port of DSPy to the BEAM35 points, September 27, 2026

Spotted in

September 27, 2026Spotted on Hacker News

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/deepfates/imp.svg?lang=en)](https://gitnova.dev/en/r/deepfates/imp)

More in this category

7.3
ollaya-dev/ollaya
A local runtime for decision models: pulls and serves classification and routing models behind a TypeSafe-compatible API. Like Ollama, but for models that return probabilities instead of text.

Early signalLanguage modelsRust+193 stars today
6.9
Niko1221/Strata
A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.

Early signalLanguage modelsC+++244 stars today
5.9
NVIDIA/Model-Optimizer
NVIDIA library for compressing and accelerating models: quantization, pruning, distillation, NAS and speculative decoding with export to TensorRT-LLM, vLLM, SGLang. For ML engineers preparing models for deployment.

BreakoutLanguage modelsPython+109 stars today
4.7
Mapika/decider
A language model that does not generate text: from a single forward pass it returns calibrated probabilities for typed questions (Choice, Score, Noul) about a given state. An open reproduction of the "System One" model…

BreakoutLanguage modelsPython+284 stars today
4.4
Rizzo-AI-Academy/rizzo-flow
A local-first implementation of the Jev idea: an LLM returns typed decisions (boolean, choice, score, numeric) with probabilities in a single forward pass, without generating tokens. Compatible with the TypeSafe HTTP…

Early signalLanguage modelsPython+59 stars today
4.4
Liuziyu77/Valen
A multimodal decision model built on a Qwen3.5-0.8B/2B backbone: it takes text, images and video with an instruction and returns probabilities over supplied candidates without generating answer tokens. The repo…

Early signalLanguage modelsPython+53 stars today