Another terminal/shell AI assistant (shell native)
ATY is a beta terminal AI assistant designed to integrate seamlessly into shell environments by building context from user input and output. It supports various interaction modes, including standard queries, reasoning tasks, and multi-step agent operations, while allowing users to choose between local and cloud-based LLM providers. The tool emphasizes speed and native feel, offering features like automatic command execution and context management to streamline terminal workflows.
- ▪ATY operates within interactive shell sessions on macOS and Linux, utilizing recent command history to provide context-aware assistance without requiring external applications.
- ▪Users can select from multiple LLM providers, including local options like Ollama and cloud services, with recommendations to use low-latency models for a responsive experience.
- ▪The assistant features distinct modes triggered by specific prefixes, such as '??' for complex reasoning and '???' for multi-step agent tasks that can utilize MCP tools.
- ▪Security warnings advise users to be cautious when using cloud providers due to the potential exposure of sensitive data in terminal outputs and to ensure Zero Data Retention is enabled.
- ▪Configuration is managed through TOML files in the user's home directory, allowing customization of model endpoints, API keys, and system prompts for different operational modes.
Hacker News (AI / LLM) files mainly under ai. We currently carry 5,678 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/TheR1D/aty |
| Publication time | Sun, 20 Sep 2026 03:55:19 +0000 |
| Retrieval time | 2026-09-20T03:58:46.920Z |
| Last seen | 2026-09-20T03:58:46.920Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 8DnN6wNgSJrT · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
ATY (beta) Another terminal/shell AI assistant, but with main focus on making AI feel fast and native to the shell. Works over SSH and other interactive shell sessions. ATY builds context from your terminal input/output, and helps without dragging you into another app or making you pipe LLM context around. Demo.mp4 Model used in demo - gemma-4-26B-A4B-it:BF16. Local models are recommended if your hardware can run them. Choose a model with low TTFT to get fast responses. You can also use cloud providers. For a responsive experience, choose one with low latency (HTTP + TTFT). WarningWhen using a cloud provider, be mindful of what you send: terminal commands and output may include secrets or private data.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.