ragweld

A tribrid RAG workbench: benchmark, debug, and ship.

Hybrid retrieval (vector + sparse + graph) with the engineering surface area you actually need in production.

Vector + Sparse + Graph Benchmarks + Evals Eval Drilldowns Run Diffs + Analysis Learning Reranker Grafana Split-view Webhooks + Alerts Memory + Multi-corpus Multi-model + Vision MCP Server
Live Demo (Faxbot + Vivified corpora)

Live search + chat are backed by the open-source Faxbot + Vivified corpora. Add ?mock=1 for offline demo mode.

What ragweld actually is

The retrieval stack matters — but ragweld’s differentiator is the engineering surface area around it: benchmarking, evaluation, diagnosis, and operations.

It’s built for senior engineers who need answers like: what changed, why did it change, and what should we try next — without guessing.

Retrieval

Hybrid + graph, fused and inspectable

Tribrid retrieval: vector + sparse + graph legs. Fuse signals, inspect sources, and tune each leg instead of treating retrieval like a black box.

Benchmarks

Measure regressions, not vibes

Run benchmarks and eval suites, then compare runs to see what changed — with drilldowns and evidence instead of guesswork.

Eval drilldown

Diff the “why”

Inspect per-query outcomes, retrieval legs, and sources. Diff runs across 200+ parameters (down to embeddings + tokenization), and get a one-click comparison summary of what likely mattered.

Reranker

Learning loop built in

Cross-encoder reranking with a feedback workflow: capture tuples, mine triplets, and compare/promote runs. Automation is first-class (cron/CI) because production doesn’t wait for a button click.

Tooltips

A built-in RAG wiki

Verbose explanations for knobs and tradeoffs — often with direct links to papers, repos, and third-party tools.

Observability

See metrics while you run

Grafana embedded in the UI (split-screen) so you can run a query, eval, or benchmark and watch live metrics in the same workspace — plus alerting hooks for production ops.

Alerts + hooks

Enterprise-grade, configurable

Alerting isn’t “on/off” — it’s your rules, your on-call. ragweld provides the plumbing: Slack/Discord webhooks and Alertmanager visibility so production incidents don’t hide in logs.

Chat + memory

A full chat interface, too

Multi-model chat (including vision inputs), persistent memory (sparse + dense), multi-corpus querying, and per-corpus embeddings/tokenization when your data demands it.

MCP

Use it anywhere

Built-in MCP server support so you can use TriBridRAG tools from other clients (IDEs, agents, automation) without rewriting integrations for each surface.

Under the hood

Tribrid retrieval is the spine: vector + sparse + graph signals fused and reranked — then surfaced through a workbench that lets you measure and iterate.

1
Index + model the corpus
Chunk into citeable spans, preserve file path anchors, and extract graph signals so you can navigate and retrieve with structure.
2
Retrieve (multi-leg) + fuse
Run sparse + vector + graph retrieval, fuse signals, then rerank candidates so answers are grounded and inspectable.
3
Evaluate + iterate
Don’t just ship a prompt. Run evals, compare runs, drill down, and tune or train the reranker based on evidence.

Choose your path

ragweld is open source and self-hostable — and we also support enterprise deployments.

Open source

Self-hosted / on-prem

MIT licensed. Run it on your infrastructure. Keep your corpora, embeddings, and model traffic where you want them.

  • • Tribrid retrieval: vector + sparse + graph
  • • Benchmark + eval suites with run comparisons
  • • Deep config + parameter glossary + tooltips
  • • Multi-corpus + per-corpus overrides
Enterprise

Managed deployments + custom integrations

For teams pushing RAG into production: deployment patterns, hardened ops, and integration work tailored to your stack.

  • • Cloud or on-prem deployments (your network, your controls)
  • • Observability + alerting hooks that plug into your on-call
  • • Benchmarks/evals as a release gate (regressions don’t ship)
  • • MCP + automation workflows for agents and internal tools

Ready to see ragweld in action?

Explore the live demo, skim the docs, and then talk to us if you’re deploying this in production.