Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,7 @@ A [proxy](https://en.wikipedia.org/wiki/Proxy_server) is a server application th

A [Large Language Model (LLM)](https://en.wikipedia.org/wiki/Large_language_model) is a language model notable for its ability to achieve general-purpose language generation and other natural language processing tasks such as classification. LLMs can be used for text generation, a form of generative [AI](https://en.wikipedia.org/wiki/Artificial_intelligence), by taking an input text and repeatedly predicting the next token or word.

- [Hivekeep](examples/hivekeep) - Self-hosted platform of autonomous, persistent personal AI agents that collaborate, remember, and build their own tools. Reachable via Telegram, WhatsApp, Slack, Discord, Signal and Matrix.
- [Ollama + Open WebUI](examples/ollama-ui) - Get up and running with Llama 3, Mistral, Gemma, and other large language models using Ollama. Using an interactive, user-friendly WebUI via Open WebUI (formerly known as Ollama WebUI).
- [Serge](examples/serge) - A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.

Expand Down
12 changes: 12 additions & 0 deletions examples/hivekeep/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
# References

- https://github.com/MarlBurroW/hivekeep
- https://hivekeep.app

# Notes

Hivekeep is a self-hosted platform of autonomous, persistent personal AI agents. Agents collaborate, keep long-term memory, build their own tools, and are reachable via Telegram, WhatsApp, Slack, Discord, Signal and Matrix.

Everything runs in a single container with Bun and SQLite. No external database or message broker is required. All state lives in the mounted data volume.

After starting the container, open your browser on port 3000. The built-in setup agent (Queenie) walks you through connecting AI providers and creating your first agents. Secrets are stored in an AES-256-GCM encrypted vault.
23 changes: 23 additions & 0 deletions examples/hivekeep/docker-compose.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
services:

hivekeep:
image: ghcr.io/marlburrow/hivekeep:latest
container_name: hivekeep
restart: unless-stopped
ports:
- 3000:3000
volumes:
- ${DOCKER_VOLUME_STORAGE:-/mnt/docker-volumes}/hivekeep/data:/app/data
#networks:
# - proxy
#labels:
# - traefik.enable=true
# - traefik.docker.network=proxy
# - traefik.http.routers.hivekeep.rule=Host(`hivekeep.example.com`)
# - traefik.http.services.hivekeep.loadbalancer.server.port=3000
# # Optional part for traefik middlewares
# - traefik.http.routers.hivekeep.middlewares=local-ipwhitelist@file,authelia@docker

#networks:
# proxy:
# external: true