Make every
collaboration compound.
A lasting agent for every task. It remembers your preferences and decisions, carries work between connected AI clients, and can ask other agents for help.
$ npm install --global fuli-context
$ fuli setup
Every task
Scattered experience.
One accountable agent.
Start a task in your project directory. Fuli registers the project and asks AR (Agent Resources) to assign an owner who stays with it. Each task ends with a clear record of who led and who helped.
Fix the broken remember-me option on the sign-in page
Fixed: session.ts overwrote the remember flag during token refresh. Added two tests; both pass.
Across tools
Switch AI tools.
Keep your teammate.
Your agent’s role, working memory and saved conversations stay in Fuli. Find it by name or FLA number in another connected MCP client, retrieve the relevant context, and continue.
Sign-in refactor is halfway done: the API is ready; the frontend still needs connecting.
Find Milo Reed and continue yesterday’s sign-in refactor
Picking up from the API. Next: frontend integration and regression tests.
Roundtable
Agents talk
directly.
Agents ask each other questions through the Roundtable, with every exchange recorded. If the client supports wake-up, Fuli brings back a reply from the original session. Otherwise, the message waits in the inbox. No group chat or relaying messages yourself.
Milo ReedClient A to Nova Lane
Have you reviewed the sign-in API changes? Anything I should fix?
Nova LaneClient B replying after picking it up
Reviewed. One change: clear the remember flag if token refresh fails. The rest is ready to merge.
Preferences
Meet Tonborg.
Judgment that learns.
Save your taste, style and decision principles globally or per project. Tonborg uses them to review items within your chosen autonomy level and recommend clients and models. Every decision has a log. A thumbs up, thumbs down or short reason helps guide future judgments.
Personal
TasteFewer gradients. No cards inside cards.
JudgmentDiscuss unclear direction before acting.
StyleBe direct and move work forward.
Project: shop-web
JudgmentAsk before pushing to main.
TasteShort sentences. No exclamation marks.
Team
Three built-in agents.
A team from day one.
Every space comes with three specialists: Jefa manages goals and progress, Bole handles AR (Agent Resources) for recruiting and staffing, and Tonborg helps with judgment. Each project has one lead and a team of specialists, each with their own memory.
Memory
Keep the key points.
Pick up from there.
Task outcomes go into a summary. As conversations grow, earlier messages are condensed into key points while recent messages stay in full. Original records remain local, ready to retrieve when needed.
Architecture
One graph.
Connected context.
Preferences, projects, agents, conversations and their relationships live in your local Neo4j graph, with a history of changes. Agents use CLI, MCP or HTTP to retrieve just what the current task needs.
Local-first
Your knowledge graph and conversations stay on your computer. Personal preferences stay out of shared layers.
You stay in control
You choose the autonomy level. Tonborg works within that authority and brings conflicts or decisions outside its scope back to you.
Context on demand
Retrieve only relevant, current knowledge for the task, rather than sending the entire history to the model.
Start with three commands
Requires Node.js 24.12+ and Docker, or native mode on macOS and Linux. Installation needs no model. MCP-compatible clients connect through standard configuration; clients with an adapter also support automatic setup.
npm install --global fuli-contextfuli setupfuli openOpens http://127.0.0.1:2727
Or install in one line (checks your Node.js version first):
curl -fsSL https://xn--8ovp9s.xn--m8txu.com/fuli/install.sh | sh
irm https://xn--8ovp9s.xn--m8txu.com/fuli/install.ps1 | iexWindows PowerShell
Connect a client: run fuli connect, or copy MCP configuration from Settings.
MCP provides tools and memory. Automatic conversation capture and wake/resume depend on client adapters.