Arthur Erlich

haylan deleted branch research/litellm-knowledgebase from haylan/LLM-Server

2026-09-03 17:35:14 +00:00

haylan deleted branch research/langchain-pgvector-vs-litellm-pgvector from haylan/LLM-Server

2026-09-03 17:35:12 +00:00

haylan deleted branch research/connecting-cloud-providers from haylan/LLM-Server

2026-09-03 17:35:12 +00:00

haylan commented on issue haylan/LLM-Server#36

2026-09-03 17:33:00 +00:00

OmniRoute: per-workload virtual keys, admin UI, and deployment shape (Docker/compose)

Second correction — the previous correction was wrong. The files exist. I'd checked the `main` branch; the original research (and this repo's actual release line) is on `release/v3.8.51`.…

haylan commented on issue haylan/LLM-Server#36

2026-09-03 17:28:21 +00:00

OmniRoute: per-workload virtual keys, admin UI, and deployment shape (Docker/compose)

Correction: the earlier resolution comment's claim that this repo's docs include STEALTH_GUIDE.md, MITM-TPROXY-DECRYPT.md, and PUBLIC_CREDS.md does not hold up. Verified directly:

A…

haylan closed issue haylan/LLM-Server#32

2026-09-03 17:24:11 +00:00

OmniRoute: can it route to arbitrary OpenAI-compatible local endpoints (llama-server), not just Ollama?

haylan commented on issue haylan/LLM-Server#32

2026-09-03 17:24:07 +00:00

OmniRoute: can it route to arbitrary OpenAI-compatible local endpoints (llama-server), not just Ollama?

Answer: No, OmniRoute is not Ollama-only. It supports arbitrary OpenAI-compatible api_base for both chat and embeddings, verified from primary source (github.com/diegosouzapw/OmniRoute, main…

haylan reopened issue haylan/LLM-Server#32

2026-09-03 17:24:04 +00:00

OmniRoute: can it route to arbitrary OpenAI-compatible local endpoints (llama-server), not just Ollama?

haylan closed issue haylan/LLM-Server#32

2026-09-03 17:23:55 +00:00

OmniRoute: can it route to arbitrary OpenAI-compatible local endpoints (llama-server), not just Ollama?

haylan closed issue haylan/LLM-Server#36

2026-09-03 17:21:22 +00:00

OmniRoute: per-workload virtual keys, admin UI, and deployment shape (Docker/compose)

haylan closed issue haylan/LLM-Server#35

2026-09-03 17:21:18 +00:00

OmniRoute: web-search tool equivalent to the SearXNG standalone endpoint

haylan commented on issue haylan/LLM-Server#35

2026-09-03 17:21:13 +00:00

OmniRoute: web-search tool equivalent to the SearXNG standalone endpoint

Answer: Yes — OmniRoute has a native standalone REST search API equivalent to LiteLLM's `search_tools`, plus its own SSRF/egress opt-in for LAN targets.

**1. Standalone REST endpoint,…

haylan commented on issue haylan/LLM-Server#36

2026-09-03 17:21:12 +00:00

OmniRoute: per-workload virtual keys, admin UI, and deployment shape (Docker/compose)

Findings (from github.com/diegosouzapw/OmniRoute, checked out at `release/v3.8.51`, its default branch)

**1. Per-workload key scoping / mintable-via-API equivalent to /key/generate: yes,…

haylan closed issue haylan/LLM-Server#33

2026-09-03 17:20:59 +00:00

OmniRoute due-diligence: maintainer, repo history, npm package trust

haylan commented on issue haylan/LLM-Server#33

2026-09-03 17:20:55 +00:00

OmniRoute due-diligence: maintainer, repo history, npm package trust

Findings

Maintainer/repo (github.com/diegosouzapw/OmniRoute): Legitimate, large, active OSS project — 60.8k stars, 8.4k forks, 550+ contributors, 8,242+ commits, MIT license, first…

haylan closed issue haylan/LLM-Server#34

2026-09-03 17:20:50 +00:00

OmniRoute: memory/knowledgebase parity with litellm-pgvector

haylan commented on issue haylan/LLM-Server#34

2026-09-03 17:20:46 +00:00

OmniRoute: memory/knowledgebase parity with litellm-pgvector

No parity — keep vendor/litellm-pgvector as-is. Researched directly from github.com/diegosouzapw/OmniRoute (docs/frameworks/MEMORY.md and docs/frameworks/LOCAL_CORPUS_CONTEXT.md, raw.githubusercon…

haylan opened issue haylan/LLM-Server#36

2026-09-03 17:18:11 +00:00

OmniRoute: per-workload virtual keys, admin UI, and deployment shape (Docker/compose)

haylan opened issue haylan/LLM-Server#35

2026-09-03 17:18:05 +00:00

OmniRoute: web-search tool equivalent to the SearXNG standalone endpoint

haylan opened issue haylan/LLM-Server#34

2026-09-03 17:17:58 +00:00

OmniRoute: memory/knowledgebase parity with litellm-pgvector

Answer: Yes — OmniRoute has a native standalone REST search API equivalent to LiteLLM's search_tools, plus its own SSRF/egress opt-in for LAN targets.

Findings (from github.com/diegosouzapw/OmniRoute, checked out at release/v3.8.51, its default branch)

Findings

Answer: Yes — OmniRoute has a native standalone REST search API equivalent to LiteLLM's `search_tools`, plus its own SSRF/egress opt-in for LAN targets.

Findings (from github.com/diegosouzapw/OmniRoute, checked out at `release/v3.8.51`, its default branch)