# microsoft/aici

AICI: Prompts as (Wasm) Programs

Repository: https://github.com/microsoft/aici
Canonical: https://ross.abutalabs.com/products/aici
Language: Rust
License: MIT
License Family: permissive
Topics: ai, rust, wasm, wasmtime, inference, language-model, llm, llm-framework, llm-inference, llm-serving, llmops, model-serving, transformer
Last push: 2025-01-22T21:14:57+00:00

## Health v2 (maintenance only)
Score: 19/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 2, release rhythm 8, longevity 76
- inputs: {"age_days": 1072, "days_push": 588, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2076, forks 86 (observed 2026-08-28T04:06:11.236924+00:00)

## What it is
AICI (Artificial Intelligence Controller Interface) is a Microsoft Research prototype that lets developers write Wasm-based controllers to constrain and direct LLM output token-by-token during inference. It integrates with engines like llama.cpp and HuggingFace Transformers, enabling constrained decoding, prompt editing, and multi-generation coordination.

## Use cases
- constrain LLM output to valid JSON or grammar formats
- run guided decoding with regex or CFG constraints
- coordinate multiple parallel LLM generations
- dynamically edit prompts and generated text during decoding
- build custom decoding strategies on top of llama.cpp or HuggingFace
- implement multi-agent LLM conversations with stateful control

## When to choose
- you need fine-grained, programmatic control over token-by-token LLM generation
- you want sandboxed controllers that run alongside the inference engine
- you need portability of decoding logic across multiple LLM serving engines

## When to avoid
- you only need constrained decoding - use the actively maintained LLGuidance instead
- you want a production-ready, stable LLM serving framework
- you need a simple prompt library without runtime decoding control

## Facets
- artifact type: framework
- maturity: experimental
- function: llm-inference, wasm, prompt-engineering, rag
- domain: large-language-models, artificial-intelligence, machine-learning, developer-tools
- platform: rust, wasm, self-hosted
- tags: constrained-decoding, llm-serving, wasm-controllers, inference-engine, microsoft-research, token-generation, linux, macos

## Member repositories
- microsoft/aici (main) score 19

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:11.236924+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:56:13.153630+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/aici (fetched 2026-08-28T04:06:11.236924+00:00, sha d0656a4a1f98)
- Data as of 2026-08-30T08:39:29.467469+00:00.