This website requires JavaScript.
9e9cac254b
feat(stack): drop qdrant and embedding-server, use OmniRoute's built-in memory
haylan
2026-09-03 22:19:21 +02:00
9e1362c22c
feat(omniroute): add dedicated embedding-server for memory feature
haylan and Claude Bot
2026-09-03 21:43:20 +02:00
885de477ba
feat(stack): bring back qdrant as OmniRoute's memory vector store
haylan and Claude Bot
2026-09-03 21:19:06 +02:00
c795993a64
fix(omniroute): publish API and dashboard ports directly, drop OMNIROUTE_PORT
haylan and Claude Bot
2026-09-03 20:49:25 +02:00
c38375c0f4
fix(omniroute): add required WS bridge secret, memory ceiling, shutdown grace period
haylan and Claude Bot
2026-09-03 20:37:49 +02:00
6132e6263e
docs: fix gateway hostname to proxy-ai.home/proxy-ai.haylan.ch
haylan and Claude Bot
2026-09-03 20:28:21 +02:00
90ef1a1061
fix(omniroute): keep the gateway published on host port 4000
haylan and Claude Bot
2026-09-03 20:17:08 +02:00
977e9d3dd7
fix(omniroute): healthcheck used python3, which the image doesn't have
haylan and Claude Bot
2026-09-03 20:08:58 +02:00
3bbda098b3
feat(stack): remove Open WebUI and Qdrant
haylan and Claude Bot
2026-09-03 19:55:31 +02:00
472e3a4738
feat(gateway): migrate LiteLLM to OmniRoute, drop the memory/knowledgebase feature
haylan and Claude Bot
2026-09-03 19:49:35 +02:00
4fe910a5f3
docs(agents): fix tea comment syntax, note map-edit race condition
haylan and Claude Bot
2026-09-03 19:29:10 +02:00
6b06d6001f
Merge pull request 'feat(llama.cpp): raise default context to 128K, document RAM/SSD offload knobs' (#30 ) from ctx-size-128k into main
haylan
2026-09-03 04:44:34 +00:00
c5864beec9
feat(llama.cpp): raise default context to 128K, document RAM/SSD offload knobs
haylan and Claude Bot
2026-09-03 06:35:48 +02:00
1eaa2a0d2e
docs(research): document opencode auto-compact trigger and config surface
haylan and Claude Bot
2026-09-03 06:25:57 +02:00
124053cf89
feat(scripts): auto-register memory-and-notes in litellm's DB for the Admin UI
haylan
2026-09-02 21:51:02 +00:00
47bdb22457
docs: record issue #24 's smoke-test findings and local litellm-pgvector patches
haylan
2026-09-02 21:32:38 +00:00
7e8b5069d4
fix(scripts): update.sh never applied litellm-pgvector's db schema
haylan
2026-09-02 21:32:33 +00:00
eaf11b6d4b
fix(scripts): ingest-memory.sh never actually computed embeddings
haylan
2026-09-02 21:32:29 +00:00
213550e44b
fix(litellm): prefix EMBEDDING__MODEL with openai/ for litellm-pgvector
haylan
2026-09-02 21:32:23 +00:00
3eda4e3ec0
fix(litellm-pgvector): honor caller-supplied id on vector store create
haylan
2026-09-02 21:32:18 +00:00
b627edb949
fix(litellm-pgvector): correct embedding vector dimension 1536 -> 768
haylan
2026-09-02 21:32:13 +00:00
ec476c7950
fix(litellm): add missing api_key to vector_store_registry
haylan
2026-09-02 21:32:08 +00:00
e2dd106f74
feat(scripts): fold model downloads into update.sh, skip if already present
haylan and Claude Bot
2026-09-02 23:07:53 +02:00
fb7cfc9148
fix(litellm): raise qwen3.8-27b-local max_tokens floor 4096 -> 16384
haylan and Claude Bot
2026-09-02 22:59:53 +02:00
30a8523433
fix(lazytainer): drop network_mode: host, join ai-stack (fixes self-ID panic)
haylan and Claude Bot
2026-09-02 22:55:38 +02:00
c7848f356a
chore(scripts): mark update.sh executable
haylan and Claude Bot
2026-09-02 22:47:53 +02:00
cb9b3a9045
fix(docs): update stale MEMORY_RETRIEVAL_EMBEDDING_KEY refs after litellm-pgvector revert
haylan and Claude Bot
2026-09-02 22:46:10 +02:00
e7983f0710
Revert "feat(knowledgebase): replace litellm-pgvector connector with memory-retrieval"
haylan and Claude Bot
2026-09-02 22:45:08 +02:00
b4dc83949e
feat(litellm): add Redis for router state/rate-limits/budgets/cache
haylan and Claude Bot
2026-09-02 22:28:25 +02:00
b996b1fe88
fix(scripts): update.sh now appends vars missing from .env, not just blank ones
haylan and Claude Bot
2026-09-02 22:21:50 +02:00
24d749b2e0
feat(scripts): fold generate-secrets.sh into update.sh, auto-mint virtual keys
haylan and Claude Bot
2026-09-02 22:18:11 +02:00
abeadc49c8
feat(knowledgebase): replace litellm-pgvector connector with memory-retrieval
haylan and Claude Bot
2026-09-02 22:09:25 +02:00
e2a79eab4a
docs(research): LangChain+pgvector-direct vs litellm-pgvector for issue #25
haylan and Claude Bot
2026-09-02 22:02:58 +02:00
7247674a9f
fix(litellm-pgvector): vendor the source instead of a remote git build context
haylan and Claude Bot
2026-09-02 21:50:45 +02:00
b0e37b2f4c
chore(scripts): add update.sh, hook it into agent/deploy workflow
haylan and Claude Bot
2026-09-02 21:44:26 +02:00
f508f5670a
feat(litellm): wire SearXNG search, pgvector knowledgebase, and memory ingestion
haylan and Claude Bot
2026-09-02 21:38:16 +02:00
a3ecbc0e02
docs(research): investigate LiteLLM knowledgebase/vector_store feature for #23
haylan and Claude Bot
2026-09-02 21:26:39 +02:00
8c42f2518b
research: LiteLLM web-search + SearXNG wiring (issue #22 )
haylan and Claude Bot
2026-09-02 21:25:30 +02:00
949802fb2b
Merge pull request 'fix(litellm): default max_tokens=4096 for the reasoning model' (#20 ) from fix/litellm-reasoning-max-tokens into main
haylan
2026-09-02 18:58:11 +00:00
100fed4274
fix(litellm): default max_tokens=4096 for the reasoning model
haylan and Claude Bot
2026-09-02 20:55:39 +02:00
7609da7dad
Merge pull request 'feat(litellm): add UI_USERNAME/UI_PASSWORD for the admin UI login' (#19 ) from fix/litellm-ui-admin-creds into main
haylan
2026-09-02 18:29:30 +00:00
ee7ebfd8e1
feat(litellm): add UI_USERNAME/UI_PASSWORD for the admin UI login
haylan and Claude Bot
2026-09-02 20:29:00 +02:00
7480a3e566
Merge remote-tracking branch 'origin/research/voidllm-evaluation'
haylan
2026-09-02 20:04:44 +02:00
9604a42e8b
Merge remote-tracking branch 'origin/research/proxy-tool-choice'
haylan
2026-09-02 20:04:44 +02:00
705019bc1c
Merge remote-tracking branch 'origin/research/proxy-shadow-pricing'
haylan
2026-09-02 20:04:44 +02:00
f40a2cff65
Merge remote-tracking branch 'origin/research/connecting-cloud-providers'
haylan
2026-09-02 20:04:44 +02:00
64243c65d7
Merge pull request 'fix(downloader): run as root to fix permission denied on models volume' (#18 ) from fix/downloader-permission-denied into main
haylan
2026-09-02 18:03:59 +00:00
7863b04787
fix(downloader): run as root to fix permission denied on models volume
haylan and Claude Bot
2026-09-02 20:03:38 +02:00
2ac4e91862
feat(chore): impelmented seecret generation
haylan
2026-09-02 19:51:54 +02:00
993f11d6de
research: Claude Pro subscription vs Anthropic API for gateway backends
haylan and Claude Bot
2026-08-26 08:51:38 +02:00
f300c5b034
research: evaluate voidllm as a LiteLLM proxy replacement
haylan and Claude Bot
2026-08-26 08:42:23 +02:00
487573c533
Add build plan documentation for 4x Radeon AI PRO R9700 rackmount LLM server
haylan
2026-08-25 07:20:58 +02:00
5cb34b19f3
Migrate Open WebUI and coding CLIs to the AI proxy (resolves #15 )
haylan and Claude Bot
2026-08-25 07:18:03 +02:00
0aefb36a48
Author LiteLLM AI proxy service (resolves #14 )
haylan and Claude Bot
2026-08-25 07:11:15 +02:00
0342090e1c
Document AI proxy request priority/queueing plan (resolves #16 )
haylan and Claude Bot
2026-08-25 07:07:20 +02:00
7e50e1867f
Document AI proxy network exposure plan (resolves #13 )
haylan and Claude Bot
2026-08-25 07:05:01 +02:00
1c29e07762
Document AI proxy key onboarding process (resolves #12 )
haylan and Claude Bot
2026-08-25 06:56:51 +02:00
a751e656e3
research: reference cloud pricing for LiteLLM shadow-cost estimate
haylan and Claude Bot
2026-08-25 06:49:38 +02:00
a1c37de6b4
research: self-hosted AI gateway/proxy tool choice — recommend LiteLLM
haylan and Claude Bot
2026-08-25 06:45:10 +02:00
c01ef8965d
Fix docs: no localhost, wire up ai.home / ai.haylan.ch via existing NPM
haylan and Claude Bot
2026-08-24 18:28:14 +02:00
7d8c9324b2
Write local-usage docs for Claude Code CLI, Kimi CLI, and OpenCode CLI
haylan and Claude Bot
2026-08-24 18:19:56 +02:00
b773d9cb8f
research: OpenCode CLI install + local llama.cpp provider config
haylan and Claude Bot
2026-08-24 18:17:14 +02:00
408a1f16ae
Ignore .claude/ worktree scratch dir
haylan and Claude Bot
2026-08-24 13:01:09 +02:00
f0e473048d
Author docker-compose stack: llama.cpp (ROCm) + Open WebUI + Qdrant + Lazytainer
haylan and Claude Bot
2026-08-24 13:01:00 +02:00
19d62aefd3
Merge branch 'research/qwen3.8-27b-tool-calling'
haylan
2026-08-24 13:00:52 +02:00
ce1ab05c3e
docs: research Qwen3.8-27B Unsloth dynamic GGUF quant + VRAM budget
haylan and Claude Bot
2026-08-24 12:16:42 +02:00
a55fbcaa18
research: Qwen3.8-27B tool-calling compat with llama.cpp Anthropic shim
haylan
2026-08-24 12:16:09 +02:00
3d768181e3
Set up agent skills config and chart wayfinder map for local AI stack
haylan and Claude Bot
2026-08-24 12:13:21 +02:00
haylan
