# Ann: Ochat — Try Ochat for terminal-based LLM workflows

**URL:** https://discuss.ocaml.org/t/ann-ochat-try-ochat-for-terminal-based-llm-workflows/17829
**Category:** Ecosystem
**Tags:** announce
**Created:** [February 19, 2026, 3:44pm UTC](https://discuss.ocaml.org/t/ann-ochat-try-ochat-for-terminal-based-llm-workflows/17829 "2026-02-19T15:44:23Z")
**Posts on this page:** 4
**Page:** 1

<div class="post-metadata">

### Author: ![dakotamurphyucf](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ocaml.org/dakotamurphyucf/32/3120_2.png) [@dakotamurphyucf](https://discuss.ocaml.org/u/dakotamurphyucf)
#### Post date: [February 19, 2026, 3:44pm UTC](https://discuss.ocaml.org/t/ann-ochat-try-ochat-for-terminal-based-llm-workflows/17829/1 "2026-02-19T15:44:23Z")

</div>

Hi all — I’d like to share a project I’ve been building: **Ochat**.

Repo: **[https://github.com/dakotamurphyucf/ochat](https://github.com/dakotamurphyucf/ochat)**  
Demo: **[https://youtu.be/eGgmUdZfnxM](https://youtu.be/eGgmUdZfnxM)**

### **What it is**

Ochat is a toolkit for building LLM workflows as **plain files**. The core format is **ChatMarkdown (ChatMD)**: Markdown plus a small, closed XML vocabulary.

A single ChatMD file is both:

- the **prompt/program** (model config, tool allowlist, instructions, context), and

- the **auditable transcript** (assistant replies + tool calls + tool outputs)

Because everything is plain text, workflows are reproducible and diffable in git.

### **Prompt packs: building larger workflows from small agents**

Ochat supports **agent-as-tool** : you can mount one ChatMD prompt as a callable tool inside another. This lets you build **prompt packs** (planner/coder/reviewer/docs/test triage/etc.) and orchestrate them from a top-level prompt, without writing a custom “agent app”.

### **chat\_tui: a Notty-based terminal UI (runtime uses Eio)**

Ochat ships an interactive terminal UI called **chat\_tui**.

- The UI is built with **Notty**

- The underlying runtime uses **Eio** (structured concurrency + I/O)

A ChatMD file can be treated as a “terminal agent”: you author an agent prompt as a .md, open it in chat\_tui, and run/iterate on it while the transcript (including tool traces) is persisted.

Some chat\_tui features:

- streaming output (assistant text + tool calls + tool outputs)

- persistent sessions you can resume/branch/export

- manual context compaction (:compact) for long histories

- syntax highlighting (including OCaml)

- AI completions in the text input (to speed up drafting)

- Vim-ish editing modes and message selection/yank/edit/resubmit workflows

### **Useful built-in tools (especially for code workflows)**

Ochat includes built-in tools that cover most “agent + repo” loops:

- read\_file / read\_dir for safe repo navigation

- apply\_patch for atomic, repo-safe edits

- webpage\_to\_markdown for high-signal ingestion (incl. GitHub blob fast-path)

- indexing/retrieval tools for grounding over docs and code

- optional vision inputs via import\_image

### **MCP tool import (optional)**

Ochat can also mount external tools via MCP (stdio or HTTP). For example, importing Brave Search over stdio:

```xml
<tool mcp_server="stdio:npx -y brave-search-mcp" name="brave_web_search" />

```

### **Quick example: a “custom terminal orchestrator agent”**

This is a complete agent definition (and becomes the runnable “app” when opened in chat\_tui):

```xml
<config model="gpt-5.2" reasoning_effort="medium" />

<!-- core built-ins -->
<tool name="read_dir"/>
<tool name="read_file"/>
<tool name="apply_patch"/>
<tool name="webpage_to_markdown"/>

<!-- optional: import an external tool via MCP -->
<tool mcp_server="stdio:npx -y brave-search-mcp" name="brave_web_search" />

<!-- prompt-pack tools (agents as tools) -->
<tool name="plan" agent="prompts/pack/plan.md" local/>
<tool name="code" agent="prompts/pack/code.md" local/>
<tool name="review" agent="prompts/pack/review.md" local/>

<developer>
You are the orchestrator. Call plan first.
Keep edits small. Before apply_patch: explain the diff and wait for confirmation.
</developer>

<user>
Add a Quickstart section to README.md.
</user>

```

Run it from the repo with:

```sh
dune exec chat_tui -- -file prompts/refactor.md

```

### **Status / caveats**

- Provider support today is **OpenAI-only**.

- The project is moving quickly.

### **Feedback / contributors**

I’d appreciate any feedback or contributions

If you try it and anything’s confusing or rough, please open an issue.

---

<div class="post-metadata">

### Author: ![Khady](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ocaml.org/khady/32/469_2.png) [@Khady](https://discuss.ocaml.org/u/Khady)
#### Post date: [February 20, 2026, 5:27am UTC](https://discuss.ocaml.org/t/ann-ochat-try-ochat-for-terminal-based-llm-workflows/17829/2 "2026-02-20T05:27:46Z")

</div>

> [@dakotamurphyucf](#):
>
> Demo: **[https://youtu.be/eGgmUdZfnxM](https://youtu.be/eGgmUdZfnxM)**

The video is private.

project looks cool. But I wonder how big are the transcripts on large runs, can you end up with GBs of text?

---

<div class="post-metadata">

### Author: ![dakotamurphyucf](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ocaml.org/dakotamurphyucf/32/3120_2.png) [@dakotamurphyucf](https://discuss.ocaml.org/u/dakotamurphyucf)
#### Post date: [February 20, 2026, 6:25am UTC](https://discuss.ocaml.org/t/ann-ochat-try-ochat-for-terminal-based-llm-workflows/17829/3 "2026-02-20T06:25:24Z")

</div>

Sorry the video is public now. Probably never in the gb range for a single transcript because it would never be larger than the max context size of the model. Also the tui stores saved sessions in a more efficient format with the option of exporting it to a raw chatmd file.

---

<div class="post-metadata">

### Author: ![dakotamurphyucf](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ocaml.org/dakotamurphyucf/32/3120_2.png) [@dakotamurphyucf](https://discuss.ocaml.org/u/dakotamurphyucf)
#### Post date: [February 20, 2026, 6:35am UTC](https://discuss.ocaml.org/t/ann-ochat-try-ochat-for-terminal-based-llm-workflows/17829/4 "2026-02-20T06:35:13Z")

</div>

[Here](https://github.com/dakotamurphyucf/ochat/blob/main/real-world-example-session/update-tool-docs/session.md) is a link to a conversation with a very large context size