01
Continue where you left off.
Move from Claude Code to Codex—or from your laptop to a remote machine—with the goal, files, decisions, and blockers from the earlier session.
Ask in your agent
Backed by
All your team’s AI work,
in one place.
Every conversation, decision, and agent run your team produces across AI tools becomes shared context - so any teammate or agent can build on what’s already been figured out, instead of starting from scratch.
Trusted by professionals and teams at
Superbuilders
Fortress
Connect the work already happening.
Connect an integration once. Nessie backfills all available history from that source, then keeps new conversations, meetings, and agent runs flowing in automatically - so your context compounds instead of scattering. No copy-pasting. No Chrome extension.
ChatGPT
Claude
Claude Code
Gemini
Perplexity
Manus
OpenClaw
Codex
Cursor
Pi
Hermes
Claude Cowork
Obsidian
GranolaChatGPT
Claude
Gemini
Perplexity
Manus
OpenClaw
Codex
Cursor
Pi
Hermes
Cowork
Claude Code
Obsidian
Granola
Nessie — ContextContext · Investor update
April investor brief
What shifted this month
- Locked the positioning line with product and sales
- Pricing landed cleanly with three design partners
- Q2 roadmap tightened around sync reliability
Open questions
- Announce Gemini integration before or after demo day?
- How to tell the local-first story to enterprise buyers?
Plug into the tools you already use.
Use /nessie in any CLI agent, or connect over MCP in ChatGPT, Claude web, OpenClaw, and other MCP clients.
CodexSKILLClaude CodeSKILLCoworkMCPChatGPTMCPClaudeMCPPerplexityMCPOpenClawPLUGINHermesPLUGINOptimizing the market-data importer
Searched recent Claude Code and Codex sessionsI found the work across your recent Claude Code and Codex sessions:
- Batched database inserts
- Reverted a larger connection pool after it caused timeouts
- Left index-write profiling unfinished
Next step: rerun the importer against the full dataset.
Debugging the token refresh race
Read Maya’s shared Claude Code sessionMaya traced the race to refresh state being cleared before persistence completed. She ruled out duplicate callbacks by logging each refresh attempt, then fixed the ordering so persistence finishes before cleanup.
Her focused tests now pass. One network-delay case still fails intermittently.
Next step: Rerun refresh-session.test.ts under throttling.
Share the right work with the right people.
Share one agent session, everything from a repository, a whole integration, or a context or folder. Give access to one person, a team, or admins only—and change or revoke it anytime. Everything else stays private.
Need to keep the whole system on your infrastructure? Talk to us about on-prem →
What people ask Nessie to do.
Start with the job, not a new system to maintain. Ask in the agent you already use; Nessie finds the sources you and your team have chosen to make available.
02
Bring your past into every new session.
Search your own conversations across ChatGPT, Claude, coding agents, and meetings. Start anywhere with what you already know—without copying, pasting, or explaining it again.
Ask in your agent
03
Reuse a teammate’s exact workflow.
Let your agent read a teammate’s shared session, recover the steps they actually took, and apply the same method instead of guessing from the final code.
Ask in your agent
04
Walk into the call briefed.
Pull the last meeting, follow-up analysis, product work, and open questions into one source-grounded brief before the next conversation starts.
Ask in your agent
05
Turn finished work into reusable context.
Package the thinking scattered across chats, coding sessions, and meetings into a decision memo, onboarding brief, or project context.
Ask in your agent
06
Improve agents from their actual traces.
Inspect what agents tried, where they failed, and which workflows repeat. Turn the pattern into a better prompt, skill, or runbook.
Ask in your agent
Questions people ask about Nessie.
What is Nessie?
Nessie is the context layer for AI-native work. It ingests all available history from the AI conversations and local sources you already use, then turns them into context you, your team, and your agents can reuse.
Is Nessie another AI chat app?
No. You keep using ChatGPT, Claude, Codex, Claude Code, Cursor, and the tools you already work in. Nessie sits above them as the shared memory and context layer.
What does Nessie sync?
Nessie ingests all available history from AI conversations, local agent sessions, Obsidian vaults, Granola meeting notes, and other integrations, then keeps new activity synced. It also tracks generated contexts, profile signals, and source metadata. You can connect multiple accounts or source roots for the same integration.
Can I use Nessie as an individual?
Yes. Nessie works just as well for one person as for a team - it unifies your own AI conversations and agent traces across every tool and makes them searchable by you and your agents. Team features like shared context are there when you need them.
Where is my data stored?
Nessie is local-first by default. Your library starts on your Mac, and Cloud Sync is optional for MCP, teams, multiple devices, and remote agent access. To generate summaries, search, and context, Nessie processes your conversations with third-party AI providers in the moment, but it never stores that content on our servers or uses it to train models.
Can anyone at Nessie see my conversations?
By default, no. Whether anyone at Nessie can read your content comes down to one setting: in Privacy Mode (the default) no one can, and your content is never used to improve our systems. If you opt into Help Improve Nessie, you choose to share some transcript snippets and usage data with us. Cloud Sync is a separate, storage-only setting: it stores your library on our servers (encrypted) so it syncs across devices, but even with Cloud Sync on, in Privacy Mode we will not look at your conversations. See our Privacy Policy for the details.
How do agents use Nessie?
Agents use Nessie through CLI and MCP. They can search your history, read full transcripts, run check-ins, resume prior sessions, and generate contexts from source conversations.
Do I need a Chrome extension?
No. Nessie ingests all available history from connected accounts, local app data, agent traces, and vault folders without asking you to copy-paste conversations into a browser extension.
Book a demo
See Nessie in action. Schedule a demo of your AI-native workflow.