Technology · Agentic → Frameworks · Open Source · wiki:deep

Rig

Rig is a Rust library for building portable LLM applications and agents with provider abstractions, tools, vector stores, RAG, and typed extraction. It brings agent patterns to performance- and safety-conscious Rust services. Candidate when worker performance, memory safety, or embedding agents inside Rust services matters. Smaller ecosystem than Python — plan integration cost honestly. ⚙️🦀 Build modular and scalable LLM Applications in Rust ✨ If you would like to help spread the word about Rig, please consider starring the repo! [!WARNING] Here be dragons! As we plan to ship a torrent of features in the following months, future updates will contain breaking changes. With Rig evolving, we'll annotate changes and highlight migration paths as we encounter them. - Table of contents - What is Rig? - Features - Runtime choices - Who's using Rig? - Get Started - Simple.

Why it matters here

In this catalog it is the Frameworks option when you need to compose multi-step agent loops and tool handoffs. Keep Rig on the observe/propose side of the loop: useful signals and drafts, with human or policy authority still required before anything irreversible runs.

How it works

Rig is a Rust agent/LLM library: provider abstractions, tools, vector stores, RAG, and typed extraction for safety-conscious services.

  1. Configure providers and tools in Rust.
  2. Build an agent or RAG pipeline.
  3. Call embeddings/vector store as needed.
  4. Return typed extracts or completions to the host service.

Related: llamaindex · topics/04-data · topics/12-central-nervous-system

Flow

When to reach for it

  • Use when: Rig is a Rust library for building portable LLM applications and agents with provider abstractions, tools, vector stores, RAG, and typed extraction matches the bottleneck and you specifically need to compose multi-step agent loops and tool handoffs.
  • Skip when: another pack already covers the need with less ops surface, or Rig would become a second place people retype truth.
  • Prefer instead: compare LlamaIndex before locking the cell.

Limits

  • Ops: confirm license, hosting, and release cadence for Rig (0xPlaygrounds/rig) before relying on it in a live corridor.
  • Integration: bad credentials, scopes, or schema drift produce empty retrievals or runaway tool/model spend without an obvious UI alarm.
  • Scope: Frameworks components support agents; they are not the company ledger or the approval authority.

What we checked

Claims below are backed by science sources on disk.

Primary / product role

Rig documentation · MODERATE

“LangChain is a framework for building agents and LLM-powered applications.”

Docs or contrast

LangChain contrast · MODERATE

“If you're looking for more advanced customization or agent orchestration, check out LangGraph, our framework for building controllable agent workflows.”

Additional source

0xPlaygrounds/rig · MODERATE

“Build modular and scalable LLM Applications in Rust”
Research inventory

9 tags · 37 out · 38 in · 3 artifacts · 1 gaps · 22 corpus docs

Catalog tags

landscape.layer
Agentic
landscape.subcategory
Frameworks
license_tag
Open Source
maps.dm
absent
maps.features
12
one_liner
Frameworks
review.depth
science
slug
rig
title
Rig

Artifacts

  • dm_map · absent
  • features_map · present · technologies/rig/features.md
  • readme · present · technologies/rig/README.md

Out · alternative_to

Out · maps_to

In · alternative_to

In · in_stack

In · maps_to

Corpus tags

category
Agentic → Frameworks
dedication
open-source
feature
agent-building-platform
agent-lifecycle
caas-platform
learning-adaptation
multi-agent-collaboration
os-agent-infrastructure
os-ai-workforce
r2-01-architecture
r2-02-assistant-expert
single-purpose-agent
wt-authoring
wt-intelligence
kind
map_edge
tech_features
tech_quote
tech_readme
needs_deepen
false
quality
ok
slug
rig
source_id
langchain-contrast
rig-docs
rig-github
technology
rig

Corpus documents (22)

map_edge · 12

  • rig → agent-building-platform
  • rig → agent-lifecycle
  • rig → caas-platform
  • rig → learning-adaptation
  • rig → multi-agent-collaboration
  • rig → os-agent-infrastructure
  • rig → os-ai-workforce
  • rig → r2-01-architecture
  • … +4 more

tech_features · 1

  • Rig · features

tech_quote · 8

  • Rig · langchain-contrast
  • Rig · langchain-contrast
  • Rig · langchain-contrast
  • Rig · rig-docs
  • Rig · rig-docs
  • Rig · rig-docs
  • Rig · rig-github
  • Rig · rig-github

tech_readme · 1

  • Rig