👁 Keep status, graphs, watches and decisions in view
Apache-2.0 · CI · Quipu stack
Rikuy is a browser brief for people using Quipu: source-bound status, graphs, watches and signed-decision client surfaces. It is a static site, not a new knowledge store. Missing evidence stays UNKNOWN. Rikuy means “to see” in Quechua.
- See work and its evidence together instead of copying headlines.
- Inspect a dated graph snapshot without treating it as live coverage.
- Keep experimental readers and signing enrollment off until your deployment admits them.
Read how it works for the client boundaries.
Requires Node 22+, Python 3, Git and npm. Rikuy has no published release
package or checksum manifest. This installer builds the current public source
snapshot, records its Git revision and package version, and copies only the
static output into ~/.local/share/rikuy/REVISION:
curl -fsSL https://raw.githubusercontent.com/scbrown/rikuy/main/install.sh | shSet STACK_INSTALL_ROOT on the receiving shell to choose another prefix. No
server, credentials or live connection are configured. Deploy the resulting
static files through your normal site lane. Never include a bearer, private key
or operator snapshot in the bundle. A versioned, checksummed release installer
remains unavailable until the project publishes its first release.
git clone https://github.com/intigraph/rikuy.git
cd rikuy
just demoValidated demo: 2 priorities and 1 decision.
Rikuy demo: http://127.0.0.1:4173
Open that address. These are validated synthetic rows, with no Quipu requests or real decisions. Stop the local demo with Ctrl-C.
| Question | Entry point |
|---|---|
| Which status can I trust? | Source configuration |
| Is this graph live? | The explorer labels its dated snapshot separately |
| Can I enable Watches or offline signing? | Only after the separate admission and enrollment checks |
| Surface | Requirement |
|---|---|
| Build and tests | Node 22+, just |
| Browser | Modern ES modules, WebAssembly and workers |
| Live reads | Admitted graph and exact named queries; credentials stay server-side |
The Quipu stack is built around a governed, bitemporal knowledge store: shared facts, decisions and work history your agents can query. Quipu can check writes against your rules, records where each fact came from, and answers what was true when.
| tool | what it gives your agents |
|---|---|
| tambo | 🧰 Agent Platform Toolkit - installs and configures the quipu stack |
| quipu | stores shared facts with provenance and history; can check writes against your rules |
| camayoc | prepares knowledge and vocabulary for Quipu, with checks before it is admitted |
| quechua | shared vocabulary and shapes for interoperable knowledge |
| chaski | reacts to graph changes and delivers governed notifications |
| bobbin | indexes your codebase and injects context from that index and Quipu knowledge |
| yupana | shows code impact and can read policies from Quipu to govern agent actions |
| desire-path | turns agent mistakes into feature requests; works on its own without Quipu |
| seeds | a work item tracker backed by the Quipu knowledge base |
| shantytown | runs crews of AI agents on work items, triggered by hand, on a schedule or by events; can share work and memory through Quipu |
| rikuy | live brief: status, graphs, watches and signed decisions over Quipu |
| shuttle | runs signed agent workflows and keeps their records in Quipu |
Load this repository’s graph: public repository-pendant publication is pending.
When an archive, checksum and provenance are published, use the
verified import workflow.
Extract the share directory before quipu import SHARE_DIR --db repository.db;
import stages knowledge and leaves ROOT unchanged.
just build
just test
just ciSee CONTRIBUTING.md and AGENTS.md.