local-deep-research vs Spanlens

local-deep-research and Spanlens are both inference engines & infra tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

local-deep-research

The tool autonomously plans and executes multi-step research tasks: it queries sources, follows citations, synthesizes findings, and returns results with full attribution — all without a cloud handoff. The vendor reports ~95% on SimpleQA benchmarks using models like Qwen3-27B on a single RTX 3090, which gives you a concrete hardware target. It pulls from 10+ search backends including arXiv, PubMed, and private document collections. Where it breaks: running capable local models demands real GPU headroom, and teams without that hardware will either throttle to weaker models or route queries to cloud LLMs — at which point the privacy guarantee depends entirely on which cloud endpoint they configure. The 109 open issues and 210 open pull requests on GitHub signal an active but fast-moving codebase; production stability requires version pinning.

Spanlens

Spanlens sits in front of your LLM provider via a single baseURL change, recording every call's cost, latency, tokens, and full request-response body with no SDK rewrite required. Agent runs surface as waterfall span trees so you can identify the one step consuming 80% of wall-clock time. The model recommender flags GPT-4o calls that look like classification tasks and shows the cost delta if you swap — with numbers from your own traffic, not benchmarks. The eval and experiment layer lets you replay a fixed dataset across prompt versions before you ship, so quality regressions don't surprise you in production. PII scanning and anomaly detection run at log time, which matters when sensitive data crosses the wire at 3 a.m. with nobody watching.

Attribute	local-deep-research	Spanlens
Pricing	Free	Paid
Price	—	$29/mo
Free trial	No	No
Open source	Yes	Yes
Has API	Yes	Yes
Self-hosted option	Yes	Yes
Platforms	Linux, macOS, Windows (via Docker, WSL2, or direct installation)	Node.js, Python, Next.js, Edge, self-hosted
Released	2024	—
Pros	Encrypted, fully local processing means documents never leave your infrastructure, so regulated or confidential data can be fed directly into research workflows without legal review of a vendor's data handling terms. Provider-agnostic model routing — llama.cpp, Ollama, OpenAI, Google, and others through a single config — so migrating from cloud to local inference when privacy requirements tighten is a configuration change, not a rewrite. 10+ search backends including arXiv and PubMed alongside private document collections, so a single research query can span published literature and internal proprietary data in one agent run rather than requiring two separate tools. Full source citations on every synthesized output, which means research results arrive with attribution intact — no manual provenance chase before you can use the findings in a paper or internal report. MIT license with self-hosted deployment means no vendor lock-in and no per-query costs as research volume scales, so teams running high-throughput literature reviews are not watching an API bill grow with every job.	Proxy-layer instrumentation via a single baseURL change, so existing code requires no structural rewrite and every provider call is captured from day one rather than after a manual instrumentation sprint. Per-user and per-route cost attribution, which means you can identify the specific customer or endpoint burning disproportionate budget before it compounds across a billing cycle. Agent waterfall trace trees with critical-path highlighting, so a slow or expensive step in a multi-agent run is pinpointed in seconds instead of reproduced manually in a staging environment. Experiment runner replays a fixed dataset across prompt versions and models with quality, cost, and latency compared side by side, which means you ship with evidence that v8 is better than v7 rather than finding out the hard way in production. Self-hosted deployment via Docker Compose under MIT license, so teams with data residency or audit requirements can run the full platform without sending trace data to a third-party cloud.
Cons	Benchmark-level accuracy (~95% on SimpleQA) is tied to running Qwen3-27B on a GPU like the RTX 3090; teams without comparable hardware that fall back to smaller models or CPU inference will see meaningfully lower result quality, and the gap is not documented per-model in the scraped source. With 109 open issues and 210 open pull requests, the codebase changes fast — teams that deploy this into production pipelines without pinning to a specific release version will encounter breaking changes between upgrades, and there is no paid support tier to escalate when something breaks. The project has no commercial backing, only donations and grants; teams that need SLA-backed uptime, security patches on a defined schedule, or vendor-supported integrations will eventually migrate to a commercial research agent — the community-only support model is the condition that triggers that switch.	PII detection is regex-based and runs at log time as a flag — not a pre-storage redaction guarantee. Teams operating under HIPAA or SOC 2 controls where sensitive data must never reach a log store, even briefly, need a dedicated redaction layer upstream of Spanlens or a different architecture entirely. The LLM-as-judge eval scoring is a single 0–1 scalar per response. Teams needing structured, multi-criteria evaluation rubrics — for example, factual accuracy scored separately from tone and policy compliance — hit the ceiling of what the built-in scorer expresses and end up maintaining a custom eval harness alongside Spanlens. At high request volumes where the proxy layer adds measurable latency to every call, teams running latency-sensitive production paths at scale have moved to SDK-side instrumentation tools or full APM platforms with LLM plugins, where the observability path is out of band rather than in the critical path.

Bottom line

Local-deep-research is free while Spanlens is paid. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between local-deep-research and Spanlens?

local-deep-research is Free and open source, while Spanlens is Paid and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is local-deep-research better than Spanlens?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.