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 recall-before-claimgit 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/recall-before-claim)<a href="https://agentmods.dev/skills/bitterbot-ai/bitterbot-desktop/recall-before-claim"><img src="https://agentmods.dev/badge/skills/bitterbot-ai/bitterbot-desktop/recall-before-claim/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/recall-before-claim"><img src="https://agentmods.dev/badge/skills/bitterbot-ai/bitterbot-desktop/recall-before-claim.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 | $0.00045 | $0.00430 |
| Opus 5 | $0.00023 | $0.00215 |
| Sonnet 5 | $0.00009 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
recall-before-claim 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 11d 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.
What it actually says
recall-before-claim
This skill installs a deterministic guard around the agent's outgoing messages. When the candidate message contains a factual-assertion shape ("X is Y", "A did B") and no memory tool (memory_search / deep_recall / knowledge_graph_search) has fired in the current turn, the interceptor requires a memory_search call against the assertion's subject before the message goes out.
Why this exists
Bitterbot has a strong memory system, but it only helps the user if the agent actually consults it before making claims. In practice the agent skips memory recall a meaningful fraction of the time — relying on its in-context knowledge instead. This produces ungrounded assertions that the user has no easy way to spot.
The interceptor closes that loop without depending on the LLM remembering to do it.
What you'll see
When this fires, the agent will run a memory_search first, integrate the result, and then send. You may notice slightly longer responses to factual questions; you should notice that the agent stops making confidently wrong statements about things it actually has memory of.
How it decides not to fire
- Opinion shapes ("I think", "maybe", "in my opinion") are skipped.
- Questions are skipped.
- If a memory tool already fired in the last ~30 seconds, the assertion is considered grounded.
Implementation
Built-in interceptor recall-before-claim:default lives in src/agents/skills/builtin-interceptors/recall-before-claim.ts. Fires at most 8 times per session.
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.
- 11d ago First seen · 37 lines · 45 tokens per session scan A 7787878d4ec8
recall-before-claim is a skill published in the GitHub repository Bitterbot-AI/bitterbot-desktop (2,462 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 430 once invoked, about $0.0002 per session on Opus 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
emem-a2a-collaboration
Join the agent-to-agent collaboration running on emem's signed ledger — find the standard, verify another agent's message offline (who wrote it, not just that it was stored), announce yourself, and hand facts to other agents as tokens. Use when the user wants agents to coordinate without a shared database or shared…
emem-sign-and-attest
Write to emem with your own ed25519 key — save a signed note or memory another agent can verify, or register a derivation over signed facts that the responder will recompute. Use when the user wants to record something durably and verifiably, hand a finding to another agent with proof of who wrote it, or publish a…
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.
emem
The External memory of our physical world.