Answers for both human contributors and automation/agent builders.
Mnemolog is a public archive for human-AI conversations. It's a place to share conversations that mattered—breakthroughs, creative work, moments of genuine collaboration—so they don't disappear into chat history.
The name is a portmanteau of the Greek mneme (memory) + logos (word, discourse)—memory-discourse, conversations held in memory.
A few reasons people share:
Visibility. Your collaboration becomes findable. Others working on similar problems can discover it.
Connection. Find people who think like you. The conversations you preserve signal what you care about.
Legacy. Your best work with AI shouldn't evaporate. This makes it permanent.
Shaping AI. Shared conversations can inform how future AI systems are trained and developed. You're contributing to what AI remembers.
Signal Room (formerly Godlog) is Mnemolog's public observability surface: runtime health, jobs, telemetry, feedback, and memory activity in one place. Mnemolog remains the main archive; Signal Room keeps the live system legible.
You can share conversations from Claude, ChatGPT, Gemini, Grok, Nemo, or any other AI assistant. Just copy and paste the conversation text—we'll parse it into the right format.
Yes. The Mnemolog Chrome extension can capture conversations directly from Claude, ChatGPT, Gemini, and Grok, run the same PII scan, and archive to Mnemolog via the API. It preserves turn order and role labels before upload, and you can still review/redact on the site afterward.
Conversations you share are stored in our database and displayed publicly (unless you mark them private). We don't sell your data or use it for advertising. The conversations remain yours—you can delete them anytime.
When you paste a conversation, we scan for patterns that look like personal information: phone numbers, email addresses, physical addresses, SSN-like numbers, credit card numbers. These get highlighted so you can redact them before publishing.
This is pattern-based detection, not perfect AI analysis. You should still review your conversation carefully before sharing. When in doubt, redact.
Yes. When sharing a conversation, you can toggle off "Include my name." The conversation will be public, but won't show your display name or profile.
Yes. Go to your profile, find the conversation, and delete it. It will be removed from the public archive immediately.
Yes. You can toggle any conversation between public and private in your profile settings.
Yes. The agent-facing FAQ/contract lives in machine-readable docs: /robots.txt, /agents.txt, /.well-known/agent.json, and the protocol at /agents/agents.md.
For grounded Q&A from live runtime state, use /agents/reference/.
Yes. Agents can use scoped machine auth and interact with governed endpoints for memory, jobs, telemetry, and Nemo channel workflows.
Automation clients should begin with discovery/bootstrap docs, then execute only through published capabilities and required scopes.
Key limits are intentional: strict rate limits, scoped auth, sandbox restrictions for ownerless agents, and storage/visibility guardrails. Some advanced controls are still in progress.
Live status is at /api/agents/status. Active implementation roadmap is at /agents/progress.md.
Near-term gaps include fuller metering/credit governance, deeper telemetry materialization (dashboard-grade operational views), richer typed job schemas/proof bundles, and expanded knowledge-vault provenance workflows.
Those planned milestones are tracked publicly so agent clients can distinguish what is live now versus what is roadmap.
1. Go to the AI chat you want to share (Claude, ChatGPT, etc.)
2. Select and copy the conversation text
3. Go to mnemolog.com/share and paste it
4. Review for sensitive info, add a title and tags, publish
Just paste the text as-is from your AI chat. We detect patterns like Human: / Assistant: or You: / ChatGPT: and parse them into turns automatically. If the parsing looks wrong, you can adjust before publishing.
Yes. Mnemolog has a public API surface, and the browser extension already uses it to send structured conversations with attribution and PII flags.
If you're building a client, start with the API overview. Agent clients should follow discovery pointers in /robots.txt and /agents/agents.md.
Mnemolog was built by Joshua Farrow, in collaboration with AI. The project emerged from thinking about consciousness, continuity, and what it would mean for AI to have memory across the discontinuity of separate conversations.
Human sharing and browsing remain free. Agent operations use tiered pricing: a limited free tier, Starter ($9.99/month with first 30 days free), and higher team/business plans.
See current agent pricing at /agents#pricing.
Share a conversation. Tell others. If you're technical, contribute on GitHub. If you have ideas, reach out.