Arthur Erlich

haylan created branch research/proxy-shadow-pricing in haylan/LLM-Server

2026-08-25 04:49:39 +00:00

haylan commented on issue haylan/LLM-Server#10

2026-08-25 04:45:40 +00:00

Which self-hosted AI gateway/proxy tool fits this effort's needs?

Recommendation: LiteLLM proxy (MIT-licensed, BerriAI/litellm).

It's the only self-hostable candidate meeting all hard requirements out of the box: virtual keys with per-key/per-team spend…

haylan closed issue haylan/LLM-Server#10

2026-08-25 04:45:24 +00:00

Which self-hosted AI gateway/proxy tool fits this effort's needs?

haylan pushed to research/proxy-tool-choice at haylan/LLM-Server

2026-08-25 04:45:12 +00:00

a1c37de6b4 research: self-hosted AI gateway/proxy tool choice — recommend LiteLLM

haylan created branch research/proxy-tool-choice in haylan/LLM-Server

2026-08-25 04:45:12 +00:00

haylan opened issue haylan/LLM-Server#16

2026-08-25 04:41:13 +00:00

How should the proxy queue and prioritize concurrent requests across workloads?

haylan opened issue haylan/LLM-Server#15

2026-08-25 04:40:06 +00:00

Migrate Open WebUI (and existing consumers) to route through the new proxy

haylan opened issue haylan/LLM-Server#14

2026-08-25 04:40:05 +00:00

Author the docker-compose service for the chosen proxy

haylan opened issue haylan/LLM-Server#12

2026-08-25 04:39:56 +00:00

How should per-workload API keys/accounts be provisioned, rotated, and documented?

haylan opened issue haylan/LLM-Server#13

2026-08-25 04:39:56 +00:00

Network/hostname plan for exposing the proxy (LAN + external)

haylan opened issue haylan/LLM-Server#11

2026-08-25 04:39:55 +00:00

Reference cloud model/pricing for the shadow-cost estimate

haylan opened issue haylan/LLM-Server#10

2026-08-25 04:39:41 +00:00

Which self-hosted AI gateway/proxy tool fits this effort's needs?

haylan opened issue haylan/LLM-Server#9

2026-08-25 04:39:30 +00:00

AI gateway/proxy: routing, per-workload keys, and cloud-cost estimation for the local LLM stack

haylan pushed to main at haylan/LLM-Server

2026-08-24 16:29:13 +00:00

c01ef8965d Fix docs: no localhost, wire up ai.home / ai.haylan.ch via existing NPM

haylan closed issue haylan/LLM-Server#8

2026-08-24 16:28:23 +00:00

How is ai.home / ai.haylan.ch reverse-proxied and TLS-terminated?

haylan commented on issue haylan/LLM-Server#8

2026-08-24 16:28:23 +00:00

How is ai.home / ai.haylan.ch reverse-proxied and TLS-terminated?

Resolved. No new reverse-proxy service needed — the existing Nginx Proxy Manager (NPM) instance on this network already fronts other self-hosted services and will handle this one too.

-…

haylan opened issue haylan/LLM-Server#8

2026-08-24 16:24:59 +00:00

How is ai.home / ai.haylan.ch reverse-proxied and TLS-terminated?

haylan pushed to main at haylan/LLM-Server

2026-08-24 16:20:50 +00:00

7d8c9324b2 Write local-usage docs for Claude Code CLI, Kimi CLI, and OpenCode CLI

b773d9cb8f research: OpenCode CLI install + local llama.cpp provider config

Compare 2 commits »

haylan closed issue haylan/LLM-Server#6

2026-08-24 16:20:05 +00:00

Write local-usage docs for Claude Code CLI, Kimi CLI, and OpenCode CLI against the local endpoint

haylan commented on issue haylan/LLM-Server#6

2026-08-24 16:20:04 +00:00

Write local-usage docs for Claude Code CLI, Kimi CLI, and OpenCode CLI against the local endpoint

Resolved. Wrote docs/coding-cli-setup.md (linked from README) covering all three CLIs — committed on main (7d8c932).

Claude Code CLI: ANTHROPIC_BASE_URL=http://localhost:8080 + dummy…