πŸ”₯ Bonfyre

Bonfyre is a behind-the-scenes engine that takes messy business input β€” calls, files, notes, recordings β€” and turns it into something useful, organized, and ready to use. No cloud bills. No vendor lock-in. Runs on your hardware.

AI That Runs On Your Machine
AI models shrunk 4Γ— so they run on laptops, phones, and small devices.
No cloud needed. Your data stays private. Models run directly on your hardware β€” even a Raspberry Pi.
A Complete Backend In 2 MB
53 binaries around a 26-module runtime that stretch from local AI to delivery.
Transcription Β· search Β· auth Β· payments Β· proxy Β· orchestration Β· telephony Β· relay Β· swarm delivery Β· verified narration β€” all local, all $0/month.
$0/monthNo cloud bills
100% privateData never leaves
20Live apps running now
15AI models published
26Shared library modules
RelayPrivate realtime media in C

What's under the hood

This isn't a wrapper around someone else's tooling. Every piece is built from scratch in C.

51
Static C binaries
Each is 20–60 KB (except the quantizer at 227 KB). No runtime dependencies. No containers. No Node.js. Just copy the binary and run it.
26
Shared library modules
Crypto, compression, threading, JSON parsing, Unicode, networking, config management, containers, CLI β€” all in one 180 KB library. Zero external dependencies beyond libc.
~2.1 MB
Total disk footprint
The entire backend β€” auth, payments, search, transcription, CMS, API gateway, compression, pipeline engine β€” fits in less space than a single JPEG photo.
5–8 ms
Per pipeline stage
Audio in, invoice out. Each processing stage completes in single-digit milliseconds. Re-runs skip unchanged stages entirely via content-addressed caching.
4Γ—
AI model compression
3-bit quantization with 0.9999+ cosine similarity. AI models that required $10K cloud GPUs now run on a $500 laptop. 15 models published on HuggingFace.
167
Tests pass
Full test suite, all reproducible from source. Every benchmark number on this site comes from scripts in the repo that you can run yourself.

Bonfyre's binaries are organized into four layers: Substrate (ingest, normalize, segment), Transform (transcribe, summarize, score, embed), Surface (format, render, deliver), and Value (price, invoice, pay, prove). Each operator declares whether it's cacheable, reversible, and idempotent β€” so the pipeline can parallelize, skip, and retry safely.

What changed since the last public push

The stack is not just bigger. The shape of the product has changed in useful ways.

Network observation became a product surface
capture β†’ recipe
BonfyreWire now fingerprints devices, emits canonical artifacts, and generates stitch-compatible recipes from owned or authorized captures. It is not just packet accounting anymore.
CLI became more operationally truthful
health-aware
`bonfyre list --health`, `bonfyre doctor sync-subcommands`, workflow listing, recipe browsing, and layer registry inspection now make the runtime easier to inspect and trust after updates.
Speech moved from feature to system
stacked
The repo now carries a deeper speech investigation story: architecture, production integration, quickstart, hypothesis engine, and discovery pipeline work, not just a standalone transcription binary.
Pages and runtime are converging
repo-aligned
The public docs, Pages workflows, and runtime packaging are being pointed at `bonfyre-oss` so the repo, the site, and the automation describe the same product instead of different snapshots.
What That Means In Practice

A week ago the public story was still mostly compression, transcription, and backend footprint. The newer repo shape adds a more operational Bonfyre: captures become artifacts, artifacts become recipes, recipes become execution plans, and the CLI now exposes more of the health and registry state needed to work with that system confidently.

bonfyre wire ingest-pcap capture.pcap --dumb-device --root layeros/state
bonfyre wire probe <capture_id> --root layeros/state
bonfyre wire artifacts <capture_id> --root layeros/state
bonfyre wire recipe <capture_id> --root layeros/state > recipe.json
bonfyre stitch plan recipe.json
See It Working Right Now
YouTube video in. Organized proof out.

The Shift Handoff app takes linked public videos, transcribes them locally, generates summaries and proof bundles, and removes the original media. Everything is traceable back to the source.

3source videos processed
24-36Γ—faster than realtime
0copies of source media kept
1 clickback to the original

What Bonfyre replaces

Real cost and complexity savings. These are real numbers.

vs Strapi (content management)
1,742Γ— smaller
500 MB install β†’ 287 KB binary. 400 npm packages β†’ 0 dependencies. Cold start 2 min β†’ instant. Dynamic schemas, token auth, REST API, full-text search β€” backed by a 26-module C runtime with its own SIMD JSON parser, BLAKE2b crypto, LZ4 compression, and work-stealing thread pool.
vs Deepgram / OpenAI (transcription)
$0 / minute
Cloud transcription at $0.006/min adds up fast. Bonfyre runs HCP-enhanced Whisper locally: speaker segmentation, filler detection, hallucination filtering via Hyperscan pattern fusion (>1 GB/s), and quality scoring with OpenSMILE eGeMAPSv02 (88 audio features). Visible metrics, not a black box. See live proof β†’
vs Pinecone (search)
$0 / month
$70–250/mo hosted vector search β†’ local NEON SIMD cosine similarity in 5 ms. Embeddings stored in zero-copy LMDB (pointer casts into mmap β€” no deserialization). BM25 text ranking for hybrid results. Runs on your machine, scales to millions of documents.
vs Twilio (phone)
No per-call billing
SaaS vendor lock-in β†’ local communications edge. bonfyre-tel handles calls, SMS, MMS, routing, and identity/event state; bonfyre-moq covers browser-native live media; fountain-coded swarm delivery helps move artifacts across unreliable links. No recurring fees, no per-minute markup.
vs full SaaS stack
$0 / month total
Auth + billing + API gateway + CMS + vector search + OpenAI-compatible proxy + local orchestration + phone edge + relay: typically multiple vendors and glue services. Bonfyre keeps those surfaces in one stack, backed by the same shared runtime, for ~2.1 MB on disk.
vs cloud AI APIs
100% private
Your data never leaves your device. You can still point existing AI clients at a local OpenAI-compatible endpoint through bonfyre-proxy, but the work stays on your hardware and can run offline when the path allows it.
vs LiveKit / Twilio Media (real-time relay)
$0 / stream
bonfyre-moq is a pure C WebTransport/MoQ relay for private realtime audio and media fan-out. No SaaS relay bill, no Node.js in production, no per-stream markup. It fits the same local-backend story as the rest of Bonfyre instead of pushing you into a separate realtime vendor stack. Details β†’

Real solutions across industries

These workflows weren't possible before β€” they needed expensive cloud GPUs or huge servers. Now they run on your laptop.

βš–οΈ Legal: Private Client Calls β†’ Organized Briefs

Record a client intake call. Bonfyre transcribes it locally (HCP Whisper with speaker segmentation), identifies key issues via BM25 ranking, scores transcript quality, and packages everything into a structured brief with content-addressed artifacts. Your client's data never touches the cloud β€” BLAKE2b hashing proves provenance.

Previously required: $400/month in cloud APIs
πŸ₯ Healthcare: Local SOAP Notes

Patient conversations transcribed and summarized into structured SOAP notes β€” all on-premise. HIPAA-compliant by default because nothing leaves the building. XSalsa20-Poly1305 encryption at rest, Ed25519 signing for audit trails. An 8 GB device runs the entire stack: transcription, summarization, quality scoring, and delivery.

Previously required: Cloud subscription + compliance overhead
πŸŽ™οΈ Podcast β†’ Monetized Asset

Drop in a raw episode β†’ get a transcript (speaker-segmented), show notes, social media clips, and a checkout page with dynamic pricing β€” all generated locally in under 5 minutes. The pipeline: bonfyre-intake β†’ bonfyre-transcribe β†’ bonfyre-summarize β†’ bonfyre-format β†’ bonfyre-offer. Each stage is content-addressed; re-runs skip unchanged work.

Previously required: GPT-4 API + Descript + manual work
🎬 Video Production: Longer, Cheaper

AI video generation models that used to need $10K+ cloud GPUs now run on a $2,000 workstation. Generate longer sequences without running out of memory β€” Bonfyre's compression makes the difference.

Previously required: Cloud GPU rental at $3–5/hour
🌍 Field Research: Record β†’ Archive β†’ Search

Record interviews in the field with no internet. Bonfyre transcribes on-device, embeds documents for SIMD vector search, creates searchable archives with zero-copy LMDB caching, and publishes a static site β€” all from a MacBook. Fountain codes handle lossy syncs back to base.

Previously required: Cloud transcription + database hosting
🏫 Education: Lectures β†’ Course Materials

Record a 90-minute lecture. Bonfyre transcribes it, generates structured notes, and produces a study guide β€” all locally. Student data never goes to any third party.

Previously required: Otter.ai subscription + manual editing
🏭 Manufacturing: Inspection Without Cloud

Run AI quality inspection on the factory floor with no internet required. A small device handles the entire model + logging + API. Fits in a 10-watt power envelope.

Previously required: Cloud GPU + internet connection
πŸ›°οΈ Defense / Remote: Air-Gapped AI

Full AI inference on hardware with no internet connection. Bonfyre's compression means large AI models now fit on portable, field-deployable devices.

Previously required: Specialized military hardware or satellite uplink
Real-Time Media, Still In The Bonfyre Style

bonfyre-moq is the realtime version of the same idea as the rest of Bonfyre: a small C binary you can run yourself. It terminates WebTransport, speaks MoQ, records stream events to SQLite, and gives you a private relay primitive for live audio, agent calls, and browser-native media flows.

Previously required: LiveKit/Twilio-style media infrastructure or a custom relay team
Technical details β†’
The common pattern

Calls, files, notes, recordings, repos, and live streams come in β†’ Bonfyre processes them locally β†’ organized output comes out as summaries, briefs, archives, pages, audio, search surfaces, and delivery flows. No cloud dependency. No recurring vendor chain.

Does my hardware work?

If you have a laptop made in the last 5 years, you can probably run Bonfyre. Here's what different hardware can handle.

What You Have What You Can Run
Raspberry Pi / 8 GB device Small AI models, local transcription, full pipeline processing
MacBook / 16 GB laptop Speech transcription + AI inference + video processing β€” all running together
MacBook Pro / 64 GB Mac Large AI models (14B parameters), full video generation, 32K-token context windows
Cloud GPU (T4 / 16 GB) Everything a 64 GB Mac can do, plus batch processing and multi-model workflows
Workstation GPU (RTX 4090+) Full video generation, multi-second sequences, all models simultaneously
The key insight

AI models that used to require expensive cloud GPUs now fit on hardware you already own. Bonfyre's compression technology makes models ~4Γ— smaller while keeping quality at 99.9%+. That's the difference between "cloud only" and "runs on your laptop."

Pick the one that matches your problem

Each is a standalone starting point β€” you don't need to understand the whole system.

Content Management

Replace bloated CMS platforms with a 287 KB binary. Dynamic schemas, token auth, REST API, full-text search β€” 1,742Γ— smaller than Strapi with zero npm dependencies. Repo β†’

Local Transcription

HCP-enhanced Whisper runs locally: speaker segmentation, filler/hallucination filtering, quality scoring (88 audio features via eGeMAPSv02). No cloud, no API keys, no per-minute charges. Live proof β†’ Repo β†’

Audio β†’ Invoice Pipeline

Drop in audio β†’ transcript β†’ summary β†’ quality score β†’ pricing β†’ packaged deliverable. 5–8 ms per stage. Content-addressed caching skips unchanged stages on re-runs. Repo β†’

Smart Search

NEON SIMD cosine similarity + BM25 text ranking. Zero-copy LMDB storage (pointer casts into mmap). Replace $250/mo Pinecone with local 5 ms queries. Repo β†’

Self-Hosted Backend

Auth, metering, API gateway, rate limiting, telephony, proxy, orchestration, work-stealing thread pools, compression, config, and CLI surfaces β€” all backed by the same shared runtime instead of a pile of separate services. Repo β†’

AI Model Compression

3-bit quantization via E8 lattice snap + ΞΌ-law warp + 16D RVQ. Cosine 0.9999+. 15 models published on HuggingFace. Run on a $500 laptop what used to require a $10K GPU. Repo β†’

OpenAI Drop-In Replacement

53 KB binary. Set OPENAI_API_BASE=http://localhost:8787. Same endpoints, local processing, $0 cost. Good when you want existing tools to keep working while Bonfyre handles transcription, briefing, and local model-facing flows underneath.

Machine-Only Orchestration

bonfyre-orchestrate is not a chat wrapper. It is a planner layer that scores pathways, stores policy memory, and decides when extra Bonfyre blocks like narrate, render, emit, or pack should be used to improve the result.

Long-Context AI

KV cache compression: 4Γ— more context tokens in the same VRAM. 9 optimization passes. Works with both nn.Linear and FPQ layers. Process entire 90-minute lectures in a single pass.

Verified Narration

bonfyre-narrate turns briefs, updates, and changelogs into audio with inline feature extraction, fidelity scoring, and refinement. It is not just β€œTTS added later” β€” it is a proof-minded output layer in the same stack.

Private Realtime Relay

Run a private WebTransport/MoQ relay in C for browser-native audio, live agent sessions, and local media fan-out. Same Bonfyre values: local-first, low overhead, SQLite logs, no recurring relay vendor tax. Docs β†’

Communications And Delivery

Use SIP where it fits, MoQ where it fits, and swarm delivery where it fits. Bonfyre now has a broader transport story: telephony, browser-native relay, QUIC-aware artifact movement, and metered peer distribution in one family.

WordPress users

Keep using WordPress for the front end. Let Bonfyre handle the heavy lifting behind the scenes.

1. Podcast β†’ blog posts

Turn episode audio into draft posts, summaries, and quotes automatically.

2. Smart site search

Search by meaning, not just keywords. Replace bloated search plugins.

3. Auto article briefs

Create editorial summaries from long transcripts or notes.

4. Premium member gateway

Back premium content tiers without plugin sprawl.

5. Lead magnet generator

Produce PDFs, EPUBs, and guides from your WordPress content.

6. Knowledge base search

Index docs, FAQs, and help content for fast retrieval.

7. Client portal backend

WordPress handles presentation. Bonfyre handles auth, metering, and deliverables.

8. Call recordings β†’ CRM notes

Raw call audio into organized, quality-scored client packets.

9. Auto-tagging archives

Enrich old content with topics, categories, and clusters.

10. Content repurposing

Turn one post into snippets, email copy, and social-ready assets.

11. Research library

Semantic index + artifact pipeline for PDFs and transcripts.

12. Proposal automation

Quoting and billing from proof bundles to invoices.

13. Voice memo publishing

Upload voice notes, publish cleaned, summarized versions.

14. Local AI features

Transcription and search without cloud APIs or vendor lock-in.

15. Fast static publishing

WordPress as editor, Bonfyre to emit alternate outputs and feeds.

Replace plugin sprawl

Typical WordPress

  • Yoast SEO β€” $99/yr
  • MemberPress β€” $179/yr
  • SearchWP β€” $99/yr
  • WP All Import β€” $99/yr
  • Gravity Forms β€” $59/yr
  • WooCommerce + 8 add-ons
  • Deepgram/Otter β€” $/min
  • Zapier β€” $49/mo
vs

Bonfyre

  • 53 binaries in the stack + 26-module runtime β€” $0/month
  • ~2.1 MB total on disk
  • Auth + billing + metering
  • Local transcription
  • Smart search
  • Multi-format output
  • Dynamic pricing
  • Zero vendor lock-in

Good fit

Publishers Agencies Course creators Membership sites Podcast networks Documentation portals Niche research sites Local businesses

Real-world recipes

You don't need to understand the technical details. Bonfyre takes your messy business input and turns it into something useful.

🏒 Property Managers

What you already have
Maintenance calls, voicemails, inspection notes, resident complaints, vendor quotes.
What Bonfyre does
Turns recordings and notes into clean summaries, searchable records, follow-up items, and downloadable packets.
What you get
Fewer missed requests, faster vendor coordination, cleaner records.
Try this
Resident leaves a voicemail β†’ upload it β†’ get a transcript, summary, issue type, follow-up notes, and maintenance packet.

🍺 Bars & Nightlife

What you already have
Staff updates, vendor calls, event ideas, shift notes, inventory issues, promo materials.
What Bonfyre does
Organizes into shift summaries, event prep notes, staff instructions, vendor records, and promo content.
What you get
Less confusion between shifts, smoother event planning, less wasted time.
Try this
Manager records a voice memo after a busy night β†’ shift recap, issue list, and event lessons-learned.

πŸ• Restaurants

What you already have
Staff training notes, supplier calls, customer comments, shift reports, menu updates.
What Bonfyre does
Turns that into clean training docs, supplier summaries, manager reports, and feedback trends.
What you get
Better staff consistency, easier training, fewer details getting lost.
Try this
Weekly manager meeting recorded β†’ clear summary, action list, staff notices, training updates.

βœ‚οΈ Salons & Barbershops

What you already have
Team updates, service notes, customer questions, training needs, promo ideas.
What Bonfyre does
Organizes into service guides, training materials, marketing drafts, and a staff knowledge base.
What you get
Faster onboarding, more consistent service, less repeated instructions.
Try this
Owner records "how we handle premium appointments" β†’ staff guide, checklist, and FAQ page.

πŸ‹οΈ Gyms & Fitness Studios

What you already have
Coach notes, member questions, program explanations, onboarding conversations.
What Bonfyre does
Creates member onboarding materials, coach summaries, training guides, searchable internal knowledge.
What you get
Better member experience, less repeated explanation, cleaner team communication.
Try this
Coach records a new class explanation β†’ member description, coaching notes, and onboarding content.

πŸ”§ Local Service Businesses

What you already have
Phone calls, job notes, technician updates, customer questions, estimates.
What Bonfyre does
Turns that into clean summaries, estimate materials, follow-up drafts, and job documentation.
What you get
Faster quoting, better follow-up, fewer details through the cracks.
Try this
Technician leaves a job-site voice note β†’ job summary, customer recap, and estimate-ready notes.

🏠 Real Estate Teams

What you already have
Showing notes, listing ideas, client calls, buyer concerns, neighborhood research.
What Bonfyre does
Organizes into client-ready summaries, listing support material, and searchable deal notes.
What you get
Better communication, faster follow-up, more polished client service.
Try this
Agent uploads buyer consultation recording β†’ needs summary, budget priorities, follow-up recommendations.

πŸ›‘οΈ Insurance Agencies

What you already have
Client calls, policy explanations, onboarding materials, renewal questions.
What Bonfyre does
Turns conversations into clear summaries, training materials, FAQ content, and intake records.
What you get
Clearer communication, easier staff training, less policy confusion.
Try this
Customer call uploaded β†’ policy discussion summary, next-step notes, follow-up checklist.

βš–οΈ Law Offices

What you already have
Client intake calls, meeting notes, matter updates, document reviews.
What Bonfyre does
Structures into organized summaries, intake records, case prep notes, and packaged materials.
What you get
More usable internal records, less time reorganizing conversations.
Try this
Client intake call β†’ transcript, intake summary, issues list, organized review packet.

πŸ₯ Medical & Dental Offices

What you already have
Staff procedures, patient education material, office training notes, admin processes.
What Bonfyre does
Turns those into reusable office guides, staff SOPs, patient handouts, and searchable documentation.
What you get
Better consistency and easier staff training.
Try this
Office manager records a front-desk process β†’ written SOP, checklist, new-staff training material.

πŸ’š Nonprofits

What you already have
Meeting recordings, community interviews, field notes, grant ideas, donor drafts.
What Bonfyre does
Turns them into reports, grant support material, board packets, and outreach drafts.
What you get
Less admin overhead, more polished outputs from a small team.
Try this
Program debrief uploaded β†’ summary, outcomes list, grant-language draft, board update.

πŸ“š Schools & Training Orgs

What you already have
Lectures, workshop recordings, training notes, teacher knowledge, learning content.
What Bonfyre does
Turns that into study guides, training documents, searchable archives, and reusable course materials.
What you get
More value from the same teaching time, easier content reuse.
Try this
Workshop recording uploaded β†’ summary, lesson notes, handout draft, archive entry.

β›ͺ Churches & Faith Communities

What you already have
Sermons, teaching notes, ministry updates, volunteer instructions, archive material.
What Bonfyre does
Turns them into summaries, newsletters, volunteer guides, and searchable ministry archives.
What you get
Better communication, easier reuse of important content.
Try this
Sermon audio uploaded β†’ transcript, summary, devotional notes, newsletter-ready content.

πŸ›οΈ Museums & Historical Groups

What you already have
Oral histories, archive notes, exhibit research, recordings, educational material.
What Bonfyre does
Organizes into searchable archives, summaries, educational packets, and public-ready content.
What you get
Preservation work that is easier to access and reuse.
Try this
Oral history recording β†’ transcript, topic summary, archive entry, exhibit-support content.

πŸ’Ό Agencies & Consultants

What you already have
Client calls, workshop recordings, sales notes, proposals, reports.
What Bonfyre does
Turns those into clean summaries, proposals, report drafts, pricing support, and client-ready deliverables.
What you get
Faster service delivery, more polished outputs from the same conversations.
Try this
Discovery call uploaded β†’ transcript, executive summary, next steps, proposal starter packet.

🎧 Clubs & Event Venues

What you already have
DJ notes, promoter messages, event recaps, guest lists, sponsor conversations.
What Bonfyre does
Turns scattered event info into organized summaries, promo assets, sponsor packets, and planning records.
What you get
Better run events, cleaner communication, faster promo cycles.
Try this
Post-event notes uploaded β†’ event summary, top issues, social post ideas, sponsor recap.

Browse all recipes β†’

20 live apps running right now

Real applications you can click and use. Each one is powered by Bonfyre behind the scenes.

Shift Handoff Board
Public videos become traceable shift cards, transcripts, briefs, and proof bundles.
Memory Atlas
Voice notes transcribed and placed on an interactive timeline.
Freelancer Evidence Vault
Client calls become timestamped invoices and proof-of-work records.
Customer Voice Board
Customer interviews distilled into a searchable insight dashboard.
Family History Museum
Family recordings organized into a browsable oral history museum.
Podcast Plant
Raw audio becomes a published podcast site with RSS feed.
Postmortem Atlas
War room recordings become searchable postmortem archives.
Explain This Repo
Source code analyzed and turned into an onboarding guide.
Town Box
Meeting recordings become public-facing town dashboards.
Grant Evidence Pack
Stories and interviews packaged into grant-ready evidence bundles.
Micro-Consulting Storefront
Package and price consulting engagements with dynamic pricing.
Personal Legal Prep Binder
Documents scored, tagged, and packed into legal-ready binders.
OSS Maintainer Cockpit
Issues and PRs turned into a searchable knowledge base.
Release-Note Radio
Changelogs narrated into audio and published as an RSS site.
Async Standup Newspaper
Voice standups analyzed and rendered as a daily newspaper.
Competitive Intelligence Scrapbook
Market data searchable in a smart intel database.
Sales Call Distiller
Sales calls analyzed, clipped, tagged, and made searchable.
Procurement Memory Site
Procurement docs embedded into a searchable ledger.
Museum Exhibit Builder
Audio clips rendered into interactive museum exhibit pages.
Local Archive Explorer
Documents indexed into a searchable local archive.

Recent additions

Newer runtime pieces and outward-facing surfaces, summarized without turning this page into release notes.

Runtime additions
Reactor, hot-load stages, coroutine pipeline flow, zero-copy cache + manifests, SIMD JSON and UTF-8, DNS, logging, mmap, MessagePack, LZ4, Bloom dedup, and the newer fountain/swarm path.
Newer product surfaces
bonfyre-proxy, bonfyre-orchestrate, bonfyre-tel, bonfyre-moq, bonfyre-swarm, bonfyre-narrate, bonfyre-quant, and bonfyre-kvcache broadened the stack beyond β€œtranscribe and summarize.”

Open source. MIT licensed. $0/month.

53 binaries in the stack. 26 shared library modules. Pages, proxy, orchestration, relay, and delivery still keep the same local-first shape.