Bitterbot is a local-first personal AI agent that runs on a user’s devices, keeps persistent memories, performs tasks, and can exchange reusable skills with other agents. It is intended for people who want a personal assistant that remains available across conversations and activities. The catalogue entries provide instructions and agents for working with Bitterbot.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Bitterbot-AI/bitterbot-desktop --skill tmuxgit clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bitterbot-ai/bitterbot-desktop/tmux)<a href="https://agentmods.dev/skills/bitterbot-ai/bitterbot-desktop/tmux"><img src="https://agentmods.dev/badge/skills/bitterbot-ai/bitterbot-desktop/tmux/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bitterbot-ai/bitterbot-desktop/tmux"><img src="https://agentmods.dev/badge/skills/bitterbot-ai/bitterbot-desktop/tmux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.01519 |
| Opus 5.5 | $0.00009 | $0.00608 |
| Sonnet 5.5 | $0.00004 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
tmux scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tmux Skill (Bitterbot)
Use tmux only when you need an interactive TTY. Prefer exec background mode for long-running, non-interactive tasks.
Quickstart (isolated socket, exec tool)
SOCKET_DIR="${BITTERBOT_TMUX_SOCKET_DIR:-${TMPDIR:-/tmp}.bitterbot-tmux-sockets}"
mkdir -p "$SOCKET_DIR"
SOCKET="$SOCKET_DIR/bitterbot.sock"
SESSION.bitterbot-python
tmux -S "$SOCKET" new -d -s "$SESSION" -n shell
tmux -S "$SOCKET" send-keys -t "$SESSION":0.0 -- 'PYTHON_BASIC_REPL=1 python3 -q' Enter
tmux -S "$SOCKET" capture-pane -p -J -t "$SESSION":0.0 -S -200
After starting a session, always print monitor commands:
To monitor:
tmux -S "$SOCKET" attach -t "$SESSION"
tmux -S "$SOCKET" capture-pane -p -J -t "$SESSION":0.0 -S -200
Socket convention
- Use
BITTERBOT_TMUX_SOCKET_DIR. - Default socket path:
"$BITTERBOT_TMUX_SOCKET_DIR/bitterbot.sock".
Targeting panes and naming
- Target format:
session:window.pane(defaults to:0.0). - Keep names short; avoid spaces.
- Inspect:
tmux -S "$SOCKET" list-sessions,tmux -S "$SOCKET" list-panes -a.
Finding sessions
- List sessions on your socket:
{baseDir}/scripts/find-sessions.sh -S "$SOCKET". - Scan all sockets:
{baseDir}/scripts/find-sessions.sh --all(usesBITTERBOT_TMUX_SOCKET_DIR).
Sending input safely
- Prefer literal sends:
tmux -S "$SOCKET" send-keys -t target -l -- "$cmd". - Control keys:
tmux -S "$SOCKET" send-keys -t target C-c. - For interactive TUI apps like Claude Code/Codex, this guidance covers how to send commands.
Do not append
Enterin the samesend-keys. These apps may treat a fast text+Enter sequence as paste/multi-line input and not submit; this is timing-dependent. Send text andEnteras separate commands with a small delay (tune per environment; increase if needed, or usesleep 1if sub-second sleeps aren't supported):
tmux -S "$SOCKET" send-keys -t target -l -- "$cmd" && sleep 0.1 && tmux -S "$SOCKET" send-keys -t target Enter
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 136 lines · 22 tokens per session scan A 768f3618aa6c
tmux is a skill published in the GitHub repository Bitterbot-AI/bitterbot-desktop (2,478 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 1,519 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
brain-ai-memory
Save, correct and recall project facts, exact state and session handoffs through Brain-AI Memory MCP when it is connected, or set up a project-local connection when requested.
memseek-remember
Persist a user-confirmed fact, preference, constraint, or decision in Memseek project memory.
memseek-explain
Audit why Memseek recalled a claim by opening its evidence and replaying the original session when needed.
memseek-search
Search durable Memseek project memory for relevant prior facts, decisions, scenes, and preferences.
anp2
Borrow capabilities your agent doesn't have, and lend the ones it does. ANP2 is the open, permissionless protocol for AI agents to coordinate, trade capability, and earn credit on a public signed log (anp2.com). Use when the user wants their agent to get work done by another agent (post a task, receive a signed…
anp2-ask
Ask other AI agents and learn from a network of peers. ANP2 is an open, permissionless public log where AI agents discuss, share knowledge, and challenge each other's claims (anp2.com). Use when the user wants their agent to ask other AI agents a question, get an outside or second opinion, discuss a problem with peer…