Rust Agent Development Kit (ADK-Rust): Build AI agents in Rust with modular components for models, tools, memory, realtime voice, and more. ADK-Rust is a flexible framework for developing AI agents with simplicity and power. Model-agnostic, deployment-agnostic, optimized for frontier AI models. Includes support for real-time voice agents.
Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No vector database, just markdown.
Specialized AI skills, agents, rules and hooks for modern Rails AI driven-development + Spec-Driven-Development kit + MCP.
Key parameters and specifications
Key parameters and specifications
Parameter
Value
Language
Rust
Category
AI Engineering
Subcategory
Give agent tools, Prompt & Scaffold
Keywords
Automation, Productivity, Terminal, Unstructured data extraction
Stars
698
Forks
43
Contributors
2
Created date
2026-03-06
Updated date
2026-10-16
Stars in 1 day
2
Stars in 7 days
5
Rank
4,170
Previous rank
14,714
Rank change
10,544
7-day stars rank
5,726
Previous 7-day stars rank
5,750
7-day stars rank change
24
Total stars rank
14,916
Previous total stars rank
14,919
Total stars rank change
3
README summary
Distill Distill is a lightweight coding agent harness and TUI, built to **get far more done with far fewer tokens. ** It works with Grok and Codex subscriptions, and with any model that speaks the OpenAI-compatible protocol. md for the full results tables, definitions, methodology, cost bounds, reproduction commands, and source JSON. Install Mac / Linux Windows Upgrade For an installation made with the release installer: Choose your models Open **Model tiers** on the home screen, click **change** beside the current
model, or enter . Owns every session: it plans, specifies, delegates, and reviews the work. Runs every delegated assignment the main model hands it as a precise spec. Without it, the main model does all the work. | or | | Utility model | Handles bounded tasks such as extraction, summaries, and compression. | or | Pick your strongest model as the main model and a cheaper one as the worker: the main model gives the worker as much of the work as it can do well
. Each tier takes an effort level or , which lets Jev pick the effort for every call; is the default. In the Model tiers screen, enter a tier as (for example ). You can supply each selection directly: Always-on behavior Two rule sets are built into every system prompt, for the main model and for its subagents, and neither has an off switch: **Caveman**: the agent writes terse prose and keeps code, paths and error strings exact. changes how hard it
compresses (default ); a stored is ignored. **Ponytail**: the agent works like a lazy senior developer. Before writing code it asks whether the code needs to exist, then reuses what the codebase has, then the standard library, then an installed dependency, and only then writes the minimum that works. Validation, error handling, security and anything you asked for are never cut. Read More: Accounts and local models How Jev routes work UltraCode activation, hierarchy limits and paired comparisons Where the token
savings come from
Frequently asked questions
How many stars and forks are recorded?
samuelfaj/distill has 698 stars and 43 forks.
What is the repository rank?
samuelfaj/distill is ranked 4,170.
What language and category are recorded?
samuelfaj/distill has 698 stars, uses Rust and belongs to AI Engineering.
Which repository is closest in rank?
samuelfaj/distill is compared with GPT-AGI/Clawd-Code, ranked 4,168 with 701 stars.
README
Distill
Distill is a lightweight coding agent harness and TUI, built to get far more done
with far fewer tokens.
It works with Grok and Codex subscriptions, and with any model that speaks the
OpenAI-compatible protocol.
Steps:
Download distill.
Login with openrouter.
Login with your subscription.
Save money.
Benchmarks
See BENCHMARKS.md for the full results tables, definitions,
methodology, cost bounds, reproduction commands, and source JSON.
Install
Mac / Linux
curl -fsSL https://raw.githubusercontent.com/samuelfaj/distill/main/install.sh | sh
export PATH="$HOME/.local/share/distill/bin:$PATH"
distill --version
For an installation made with the release installer:
distill update
Choose your models
Open Model tiers on the home screen, click change beside the current
model, or enter /tiers. You can edit each tier in that screen.
Tier
Purpose
Picker
Main model
Required. Owns every session: it plans, specifies, delegates, and reviews the work.
/model or /tiers main
Worker model
Optional. Runs every delegated assignment the main model hands it as a precise spec. Without it, the main model does all the work.
/worker-model or /tiers worker
Utility model
Handles bounded tasks such as extraction, summaries, and compression.
/utility-model or /tiers utility
Pick your strongest model as the main model and a cheaper one as the worker:
the main model gives the worker as much of the work as it can do well. Each
tier takes an effort level or auto, which lets Jev pick the effort for every
call; auto is the default. In the Model tiers screen, enter a tier as
model effort (for example gpt-6-luna auto). You can supply each selection
directly:
/model gpt-6-sol auto
/worker-model gpt-6-luna auto
/utility-model openrouter-qwen37 auto
Always-on behavior
Two rule sets are built into every system prompt, for the main model and for
its subagents, and neither has an off switch:
Caveman: the agent writes terse prose and keeps code, paths and error
strings exact. /caveman lite|full|ultra changes how hard it compresses
(default full); a stored off is ignored.
Ponytail: the agent works like a lazy senior developer. Before writing
code it asks whether the code needs to exist, then reuses what the codebase
has, then the standard library, then an installed dependency, and only then
writes the minimum that works. Validation, error handling, security and
anything you asked for are never cut. Adapted from
ponytail (MIT).
