Examples

LLM wiki pattern

kiwifs init --template knowledge --root ./knowledge

Directory structure

knowledge/
├── SCHEMA.md
├── index.md
├── log.md
├── pages/
├── episodes/
└── .kiwi/playbook.md

Call kiwi_context on connect, then follow playbook operations. See Agent playbook.

Agent writes

REST — single file

curl -X PUT 'http://localhost:3333/api/kiwi/file?path=pages/auth.md' \
  -H 'X-Actor: my-agent' \
  -H 'X-Provenance: run:run-249' \
  -d '# Authentication

OAuth2 + JWT.'

REST — bulk write (one commit)

curl -X POST 'http://localhost:3333/api/kiwi/bulk' \
  -H 'Content-Type: application/json' \
  -d '{
    "files": [
      {"path": "pages/auth.md", "content": "# Auth\n\nUpdated."},
      {"path": "log.md", "content": "- 2026-05-21: updated auth"}
    ],
    "actor": "agent:exec_abc",
    "message": "run 249"
  }'

Filesystem mount

echo "# Finding" > /mnt/kiwi/pages/finding-042.md

Query provenance

curl 'http://localhost:3333/api/kiwi/meta?where=$.derived-from[*].id=run-249'

MCP tool sequences

First connection

kiwi_context

Ingest a source

kiwi_search("authentication")
kiwi_write("pages/auth.md", content)
kiwi_read("index.md")
kiwi_write("index.md", updated)
kiwi_append("log.md", "- added auth")

Answer a question

kiwi_search("payment timeout")
kiwi_read("pages/payments.md")

Remember (episodic)

kiwi_append("episodes/2026-05-21.md", observation)

Consolidate episodes

kiwi_memory_report
kiwi_read("episodes/2026-05-21.md")
kiwi_write("pages/topic.md", merged_content_with_merged_from)

See Episodic memory.

Health check

kiwi_analytics
kiwi_health_check("pages/auth.md")
kiwi_lint

DQL

kiwifs query 'TABLE title, status FROM "pages" WHERE status = "draft" SORT priority DESC'

kiwifs query 'COUNT FROM "pages" GROUP BY status'

curl 'http://localhost:3333/api/kiwi/query?q=TABLE%20title%20FROM%20%22pages%22'

Aggregation

kiwifs aggregate --group status --calc count,avg:priority

Import

kiwifs import --from postgres --dsn "postgres://..." --table users --root ./knowledge

kiwifs import --from obsidian --path ~/vault --root ./knowledge

kiwifs import --from csv --path data.csv --root ./knowledge --dry-run

Export

kiwifs export --format jsonl --include-content -o knowledge.jsonl

kiwifs export --format jsonl --include-embeddings -o vectors.jsonl

curl -X POST 'http://localhost:3333/api/kiwi/export/document' \
  -H 'Content-Type: application/json' \
  -d '{"format":"pdf","path":"pages/report.md"}' -o report.pdf

See Document export.

Production config

.kiwi/config.toml

[server]
public_url = "https://wiki.example.com"

[search]
engine = "sqlite"

[search.vector]
enabled = true

[search.vector.embedder]
provider = "ollama"
model = "nomic-embed-text"

[versioning]
strategy = "git"

[backup]
remote = "git@github.com:org/knowledge.git"
interval = "5m"

Docker

docker run -d --restart always \
  -v /data/knowledge:/data \
  -p 3333:3333 \
  ameliaanhlam/kiwifs serve --root /data

Go embed

import "github.com/kiwifs/kiwifs/pkg/kiwi"

srv, err := kiwi.New("/data/knowledge", kiwi.WithSearch("sqlite"))
mux.Handle("/wiki/", http.StripPrefix("/wiki", srv.Handler()))

See Go embed and Alternate protocols.

Getting Started

Core Concepts

Guides

Data Import

Data Export

Deployment

LLM wiki pattern

Agent writes

MCP tool sequences

DQL

Aggregation

Import

Export

Production config

Docker

Go embed

​LLM wiki pattern

​Agent writes

​MCP tool sequences

​DQL

​Aggregation

​Import

​Export

​Production config

​Docker

​Go embed

LLM wiki pattern

Agent writes

MCP tool sequences

DQL

Aggregation

Import

Export

Production config

Docker

Go embed