capability-gap analysis + improvement plan · researched 2026-09-10 · nothing installed yet

IMPROVEMENT ROADMAP

What this rig already has

Six LLMs (262K–1M context) behind one authenticated endpoint, tool calling, vision, embeddings, reranking, live model-swap serving, an agent-profile integration, and a comparison playground. Media-gen research done (installing separately). What follows is what's missing — ranked by capability-per-effort.

Ranked: what to add next

1. Native MCP + built-in tools on the endpoint hours · ~0 RAM

llama-server became a self-contained agent host in July 2026 (upstream PR #26062): --mcp-servers-config attaches stdio MCP servers, --tools/--agent exposes filesystem/shell tools directly from the endpoint. Biggest capability jump per minute spent — every connected agent (Hermes included) inherits server-side tools without any client changes.

Caveat: built-in exec_shell_command is unsandboxed and the rig is tailnet-exposed. Pair with the API key (done) + a prompt-guard pass before widening access.

2. Qdrant — persistent vector store ~1 hr · 1–2 GB

The rig has embeddings and reranking but nothing persists vectors. Qdrant (Apache-2.0, single binary/container) is the foundation both RAG and memory layers want. Feeds from the existing embed endpoint; queried through the existing reranker.

3. mem0 — persistent memory layer ~2 hrs · <1 GB

The remaining fully-self-hostable memory layer (Zep killed its Community Edition in 2026). Defaults to Qdrant — reuses #2 directly. Gives agents durable memory across sessions against the OpenAI-compatible endpoint.

Caveat: mem0's benchmark numbers are vendor-reported (independent LongMemEval score ≈ 49 vs claimed 94). Evaluate on your own data before trusting it.

4. Document RAG engine 1–2 days · pick by corpus

Three shapes, all consume the existing endpoints as-is:

EngineLicenseFootprintBest for
KhojAGPL~4 GBpersonal notes / Obsidian vault
RAGFlowApache-2.016 GB+ multi-containerscanned PDFs, tables, heavy docs
LightRAGMITlightgraph-style multi-hop Q&A

Decision hinges on what corpus goes on this box first.

5. Observability — Arize Phoenix ~1 hr · <1 GB

Zero tracing today. Phoenix (OTel-native) traces every call through llama-swap and ships free RAG-relevance / hallucination evals. Langfuse (MIT) only if scale demands its ~6 GB ClickHouse stack.

6. Bonus: LoRA fine-tuning on this box feasible now

Unsloth QLoRA runs on gfx1151 (verified by community May 2026 via TheRock ROCm builds) — up to ~70B-class models at 4-bit within ~80 GB peak. Train while LLMs are swapped out. The pip environment is fragile — containerize if pursued.

Evaluated and not recommended (with reasons)

Full research

Per-gap tables, licenses, memory budgets, sources, and UNVERIFIED flags: research/capability-gaps.md in the build repo. Media-gen track: Media Gen Roadmap.