Wynba

A Rust coding agent with tool use and SQLite-backed sessions. It runs on your machine, edits real files, searches your codebase, runs commands, spawns sub-agents, and searches the web — all from a fast TUI (or plain REPL).

Features

• Terminal UI — streaming markdown, tool-call blocks with diffs, a Grok-Build-style prompt editor with paste chips, image paste, a status bar and scrollable history. Falls back to a plain REPL when stdin isn't a terminal, and to a one-shot mode when you pass a message on the command line.
• 15 built-in tools — read_file, write_file, edit_file, delete_file, list_files, search, run_command, task (sub-agents), web_search, web_fetch, todowrite, todoread, plus the goal tools create_goal, update_goal, get_goal.
• Sub-agents — the task tool can launch general (full tool access) or explore (read-only research) sub-agents with their own prompts, capped at a max nesting depth.
• Todos — opencode-style task tracking: todowrite creates/updates a structured per-session task list (content/status/priority, statuses pending/in_progress/completed/cancelled), todoread reads it back. Persisted in SQLite so the list survives compaction and relaunches.
• Goals — opencode-style long-running goals: /goal <objective> sets a goal and the agent keeps working across turns (tracking time used and iteration count) until it's complete, blocked, paused, or cleared. Manage it with /goal status, /goal pause, /goal resume, /goal clear; the agent itself uses create_goal/update_goal/get_goal. Goals are stored per session in SQLite.
• Sessions — every conversation and tool result is persisted to SQLite. Create, list, show, resume, revert, and fork sessions at any point in the history.
• Many providers — OpenAI-compatible APIs, Anthropic, Gemini, and Bedrock wire formats, plus a large registry of providers (see Providers). Retries with exponential backoff are built in.
• Context management — the message history sent to the model is bounded by round and byte budget so long, tool-heavy runs don't overflow the context window.
• Steering — queue follow-up messages (Alt+Enter) while the agent is running, or type to steer the running agent mid-turn; interruptions (Esc) restore the prompt editor.
• File safety — edits and writes are backed up per session so you can revert a turn (and its file changes) with one command.
• Themes — popular palettes built in (Dracula, One Dark, Gruvbox, Nord, Solarized, Tokyo Night, Catppuccin, Monokai, GitHub Dark, Rose Pine — each repaints the full UI including the background) plus custom themes in ~/.wynba/themes/*.json, switchable live with /theme.
• Images — paste images from the clipboard (Ctrl+V) into your prompt on vision-capable models; stored per message and sent in each provider's native format.

Installation

One-line install (macOS and Linux, picks the right binary from releases):

curl -fsSL https://raw.githubusercontent.com/flaxodotdev/wynba/main/install.sh | sh

Or download the binary for your platform from GitHub Releases.

From source (requires a recent stable Rust, the crate uses the 2024 edition):

git clone <this-repo>
cd wynba
cargo build --release
# binary at target/release/wynba

Run the tests with:

cargo test

Quick start

wynba

On first launch you'll get a new session. Connect a provider (interactively) or set an API key as an environment variable, then chat:

• /connect — searchable provider picker, then enter credentials. Credentials are stored in the local database.
• or set the matching env var, e.g. export OPENAI_API_KEY=..., and the provider is ready to use immediately.

Example one-shot use:

wynba "explain how the revert command works"
wynba chat -s 1 "continue"
wynba --session <uuid> "what did we change last?"

CLI

wynba [OPTIONS] [COMMAND] [MESSAGE...]

Global options:

Option	Description
--db <PATH>	Path to the SQLite database (default ~/.wynba/agent.db, or $WYNBA_DB)
--provider <N>	Provider to use (default from $DEFAULT_PROVIDER, else openai)
--model <N>	Model name, overrides the provider default
--session <UUID>	Resume an existing session by UUID (REPL or one-shot)
--theme <NAME>	Theme name: a built-in palette (default, dracula, one-dark, …) or a ~/.wynba/themes/*.json name
-h, -V	Help / version

Subcommands:

Command	Description
new [--name N] [MSG]	Create a new session (interactive or with a message)
list	List all sessions
show <SESSION>	Show the full message history of a session
chat [-s ID] [MSG]	Chat in an existing session (by numeric id) or create one
delete <SESSION>	Delete a session and all its messages
connect	Interactively connect a provider
login [PROVIDER]	Sign in like fx.sh: vercel (default), codex, grok
logout [PROVIDER]	Sign out of a provider
provider [NAME]	Switch provider (gateway, codex, grok) like fx.sh
models	List the active provider's model catalog
status	Show provider, model and credential status
providers	List providers and their credential env vars
resume	List sessions and pick one to continue

<SESSION> accepts either a UUID or a numeric id.

TUI usage

Inside the interactive TUI:

• Enter — send. Shift+Enter or \+Enter — newline.
• Alt+Enter — queue a follow-up message (delivered when the agent finishes).
• Enter while the agent is busy — steer it: the text is folded into the conversation before the next LLM call.
• Esc Esc — stop the current reply; Escape never quits the session.
• ↑/↓, mouse wheel — scroll the history.
• Ctrl+V — paste text or an image from the clipboard (images on vision-capable models).
• Select a past user message to revert (restores its file changes too) or fork a new session from that point.

Slash commands

Command	Description
/connect	Interactively connect a provider
/login	Provider picker, fx.sh style (vercel, codex, claude, grok)
/login <provider>	Sign in to one provider directly
/provider	Switch provider (gateway, codex, claude, grok) like fx.sh
/status	Show provider, model and credential status
/logout	Log out of a provider (vercel, codex, claude, grok)
/model <name>	Switch model directly (or /model to pick from the provider's model list)
/theme <name>	Switch theme directly (or /theme for a live preview picker)
/new	Start a new session
/resume	Pick a saved session and continue it
/import	Import a session from another agent harness (Claude Code, Codex, OpenCode, Pi, GrokBuild)
/import <name>	Import from a specific harness (claude-code, codex, opencode, pi, grokbuild), --last for the most recent
/redo	Re-apply the last /undo, or restore the last reverted messages
/undo	Restore files the last agent response changed (via git)
/goal <objective>	Set a long-running goal the agent works toward across turns
/goal status

Undo / redo. Because the agent can change files through tools and shell commands, /undo reverses the last response's file changes with git: before each run the whole working tree (tracked files, deletions and untracked non-ignored files, across the whole repository) is snapshotted into a throwaway git commit-tree object, and /undo restores it with git read-tree + checkout-index + clean. HEAD and your commit history are never touched, and your session transcript is kept. /redo re-applies what /undo took back. Undo works anywhere inside a git repository (even from a subdirectory); outside one it has nothing to do. Notes: ignored files (e.g. node_modules, build output) are never touched, and any untracked files created after the run — not just the agent's — are removed by /undo, so commit or stash anything you care about before running it.

When the provider rejects a request because the history no longer fits its context window, the agent auto-compacts — the older turns are folded into a summary, exactly like /compact — and retries the turn once (mirroring pi's overflow recovery). If the provider instead reports an output token limit (finish_reason=length with no content, usually thinking eating the whole budget), raise MAX_TOKENS or lower thinking effort with /effort.

Providers

Credential env vars (run wynba providers for the full list with default models). The most common are:

Provider	Env var	Notes
OpenAI	OPENAI_API_KEY	also OPENAI_BASE_URL, OPENAI_MODEL
Anthropic	ANTHROPIC_API_KEY	also ANTHROPIC_BASE_URL, ANTHROPIC_MODEL
Google Gemini	GOOGLE_API_KEY / GEMINI_API_KEY	also GOOGLE_MODEL
Groq	GROQ_API_KEY
Mistral	MISTRAL_API_KEY
xAI (Grok)	XAI_API_KEY
DeepSeek	DEEPSEEK_API_KEY
Ollama	(none)	defaults to http://localhost:11434/v1
LM Studio	(none)	defaults to http://localhost:1234/v1
Amazon Bedrock	AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY	native Bedrock format
Google Vertex	GOOGLE_VERTEX_TOKEN	native Gemini format
Azure OpenAI	AZURE_OPENAI_API_KEY	full chat-completions URL
Vercel Gateway (fx)	AI_GATEWAY_API_KEY or fx/wynba login	shares ~/.fx/auth.json with fx
Codex subscription	ChatGPT subscription (wynba login codex)	shares ~/.fx/chatgpt-auth.json with fx, falls back to ~/.codex/auth.json
Claude subscription	Claude subscription (wynba login claude)	reuses the Claude Code CLI session in ~/.claude/.credentials.json
Grok subscription	Grok subscription ()

Subscription providers work just like in fx.sh: /login opens the provider picker (Vercel AI Gateway, Codex, Claude, Grok), wynba login <provider> signs in directly, wynba provider <gateway|codex|claude|grok> (or /provider in the TUI) switches between them, and wynba status (or /status) shows what's connected. Model catalogs come from each provider's authenticated endpoint, and per-provider model choices are shared with fx via ~/.fx/settings.json.

General settings:

• DEFAULT_PROVIDER — default provider name (default openai).
• MAX_TOKENS — max output tokens for the chat call (default 16384).
• WYNBA_DB — override the SQLite database path.

Each provider also honors <PROVIDER>_BASE_URL and <PROVIDER>_MODEL env vars (see resolve_provider in src/llm.rs). The broad registry of additional providers comes from Mastra's provider registry and is generated by scripts/gen_providers.py into src/llm/providers_data.rs — don't edit that file by hand.

Model selection uses the provider's live /models endpoint when available and falls back to the embedded registry.

Theming

The agent ships with a set of built-in popular palettes — every one overrides the full color map, so switching themes repaints the whole UI including the full-screen background. Available out of the box:

default, dracula, one-dark, gruvbox-dark, solarized-dark, nord, tokyo-night, catppuccin-mocha, monokai, github-dark, rose-pine, cursor (a port of the Cursor editor's dark theme — near-black surfaces, electric-blue #4d9eff accent for AI/highlights, and Cursor's exact diff greens/reds).

On top of those, custom themes are JSON files in ~/.wynba/themes/*.json. Every field is optional and falls back to the built-in default palette. Values are 6-digit hex strings (#rrggbb). Example:

{
  "name": "rose",
  "accent": "#ff6b9d",
  "border": "#4a4a55",
  "user_bg": "#3a2b38",
  "md_green": "#b5bd68"
}

Available fields include bg (the full-screen interface background — like Grok Build, the TUI paints its own background instead of inheriting the terminal's), plus border, accent, muted, dim, text, user_bg, user_fg, tool_pending_bg, tool_ok_bg, tool_err_bg, tool_title_fg, tool_call_fg, tool_args_fg, tool_out_fg, tool_err_fg, diff_add_fg, diff_del_fg, diff_hunk_fg, diff_add_bg, diff_del_bg, subagent_pending_*, subagent_ok_*, sel_bg, sel_fg, revert_bg, revert_fg, and md_* colors. Pick one with /theme (live preview) or set it at launch with --theme <name>. The active theme is persisted in the settings table.

Storage

• Database — SQLite at ~/.wynba/agent.db (override with --db/WYNBA_DB). Holds sessions, messages, provider configs, file backups, settings, per-session todos, and per-session goals.
• Themes — ~/.wynba/themes/ plus the built-in palettes in src/theme.rs.
• File backups — ~/.wynba/backups/<session_id>/, used to undo a turn's file changes when you revert.

Project layout

src/
  main.rs        CLI, REPL/TUI loop, slash commands, session management
  agent.rs       agent loop: system prompt, tool rounds, steering, sub-agents
  tools.rs       tool definitions, execution, diff engine
  llm.rs         provider adapters, retries, model listing
  llm/providers_data.rs  generated provider registry (see scripts/)
  db.rs          SQLite schema and queries
  goal.rs        long-running goals: template, continuation prompt, statuses
  tui.rs         terminal UI: editor, streaming render, tool blocks
  md.rs          streaming markdown renderer
  theme.rs       color themes
scripts/
  gen_providers.py  regenerates src/llm/providers_data.rs from Mastra's registry

License

No license file is currently specified in this repository.