burnban vs PixelRAG

burnban and PixelRAG 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.

burnban

Burnban reads supported agent log files already sitting on disk, prices the recorded usage against public API list rates, and lets you set daily, weekly, monthly, or per-agent spend caps enforced in the request path — all from a local dashboard at localhost:4141. The ledger is SQLite on your machine. No keys leave to a Burnban server, no prompts hit a control plane, no account is required. The sharp edge is the word 'supported': log format and provider coverage are scoped, and anything outside that scope remains invisible to the meter. Teams tracking unsupported agents or providers find Burnban shows them a partial picture.

PixelRAG

PixelRAG is an open-source retrieval framework that indexes document pages as images and searches over them using vision-language models, so structure that defeats text extraction — column layouts, embedded charts, dense tables — stays intact through the retrieval step. The hosted API requires no key and the pip-installable package supports self-hosted deployments, which means teams can run it locally without routing data through external services. Where it fits cleanly: Wikipedia-scale visual QA and any RAG pipeline where the page's visual structure carries meaning the text alone loses. Where it breaks: the screenshot-per-page approach trades token efficiency gains on visual content against higher compute per retrieved chunk, and the evidence base for how it performs past Wikipedia-scale collections is thin. Teams pushing beyond the documented use cases are largely on their own.

Attribute	burnban	PixelRAG
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	Yes
Self-hosted option	Yes	Yes
Platforms	macOS, Linux, Windows	Linux, macOS (Apple Silicon supported)
Pros	Zero-telemetry local enforcement, so your API keys, prompts, and responses never touch a Burnban server — eliminating the trust risk that comes with cloud-based spend gateways. Daily, weekly, monthly, and per-agent spend caps enforced in the request path, so a runaway agent gets blocked before it runs up the bill rather than flagged after the invoice arrives. The subsidy repricing command converts historical log data into a qualified, shareable cost estimate against any supported model's public rates, so you can surface the real cost of local agent activity to stakeholders without needing provider-side billing access. MIT licensed single binary with checksum verification and published SBOMs, so teams with strict supply-chain policies can audit exactly what sits in their provider request path. Local SQLite ledger requires no account, signup, or cloud dependency, which means the tool keeps working when a vendor changes pricing, shuts down, or decides to monetize the data flowing through their gateway.	Retrieves over rendered page images rather than extracted text, so tables, charts, and multi-column layouts that break text parsers are preserved through the retrieval step — meaning answers that live inside visual structure are actually findable. No-key hosted API plus open-source pip install, so you can prototype against the hosted endpoint and shift to a self-hosted deployment without changing your retrieval logic or negotiating access. Designed to feed page screenshots directly into VLMs like Claude, which means you skip the OCR-then-chunk pipeline and give the model the same rendered context a human reader would see. Self-hosted option available, so document collections that cannot leave your infrastructure can use the same retrieval approach without routing pixels through external APIs. Open-source codebase, so teams that hit a wall with the default behavior can inspect and modify the retrieval logic rather than waiting on a vendor roadmap.
Cons	Enforcement only applies to traffic routed through the local meter — agents or apps that call providers directly bypass all caps entirely, so a team with more than one or two agents faces a partial blind spot from day one. Log reading and traffic enforcement are scoped to 'supported' agents and providers; the docs do not enumerate a complete compatibility list on the landing page, so teams discover unsupported tools by finding gaps in the dashboard rather than a checklist upfront. Because Burnban is a V0.4 single-maintainer project with no API surface and no integrations layer, teams that outgrow personal spend monitoring and need org-level cost allocation, multi-seat dashboards, or CI budget gates will find nothing here to extend — at that scale they migrate to a platform with an admin layer, and Burnban becomes a retrospective curiosity. The model repricing and subsidy features produce estimates explicitly qualified as 'API-equivalent' against list rates, not actual billed amounts — teams using negotiated pricing or credits will find the numbers systematically off, making the output useful for illustration but unreliable for finance reconciliation.	Vision inference per retrieved chunk is computationally heavier than text embedding lookups — at collection sizes or query volumes beyond Wikipedia-scale test cases, there is no documented throughput data, and teams hitting latency walls have no vendor benchmarks to plan against. The project pages and community footprint are small enough that debugging non-obvious failures — unusual document formats, retrieval misses on edge-case layouts — means reading source code, not consulting a forum. Teams that need fast answers on production incidents switch to frameworks with active communities and paid support tiers. The retrieval framework does not include chunking strategy guidance for documents where a single page contains multiple independent topics; teams assembling a full RAG pipeline still have to solve page segmentation and context windowing on their own.

Bottom line

Only PixelRAG exposes a public API. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between burnban and PixelRAG?

burnban is Free and open source, while PixelRAG is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is burnban better than PixelRAG?

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.