pyr0ball
dc4a08c063
- setup.sh: replace docker-image-based NVIDIA test with nvidia-ctk validate
(faster, no 100MB pull, no daemon required); add check_docker_running()
to auto-start the Docker service on Linux or warn on macOS
- prepare_training_data.py: also scan training_data/uploads/*.{md,txt}
so web-uploaded letters are included in training data
- task_runner.py: add prepare_training task type (calls build_records +
write_jsonl inline; reports pair count in task result)
- Settings fine-tune tab: Step 1 accepts .md/.txt uploads; Step 2 Extract
button submits prepare_training background task + shows status; Step 3
shows make finetune command + live Ollama model status poller
|
||
|---|---|---|
| app | ||
| config | ||
| data/survey_screenshots | ||
| docker | ||
| docs | ||
| scrapers | ||
| scripts | ||
| tests | ||
| .dockerignore | ||
| .env.example | ||
| .gitignore | ||
| CHANGELOG.md | ||
| CLAUDE.md | ||
| compose.podman-gpu.yml | ||
| compose.yml | ||
| CONTRIBUTING.md | ||
| Dockerfile | ||
| Dockerfile.finetune | ||
| environment.yml | ||
| LICENSE-BSL | ||
| LICENSE-MIT | ||
| Makefile | ||
| mkdocs.yml | ||
| pytest.ini | ||
| README.md | ||
| requirements.txt | ||
| setup.sh | ||
Peregrine
AI-powered job search pipeline — by Circuit Forge LLC
"Don't be evil, for real and forever."
Automates the full job search lifecycle: discovery → matching → cover letters → applications → interview prep. Privacy-first, local-first. Your data never leaves your machine.
Quick Start
1. Install dependencies (Docker, NVIDIA toolkit if needed):
git clone https://git.circuitforge.io/circuitforge/peregrine
cd peregrine
bash setup.sh
2. Start Peregrine:
make start # remote profile (API-only, no GPU)
make start PROFILE=single-gpu # with one GPU
make start PROFILE=dual-gpu # dual GPU (Ollama + vLLM)
3. Open http://localhost:8501 — the setup wizard guides you through the rest.
macOS: Docker Desktop must be running before
make start. Windows: Not supported — use WSL2 with Ubuntu.
Inference Profiles
| Profile | Services started | Use case |
|---|---|---|
remote |
app + searxng | No GPU; LLM calls go to Anthropic / OpenAI |
cpu |
app + ollama + searxng | No GPU; local models on CPU (slow) |
single-gpu |
app + ollama + vision + searxng | One GPU: cover letters, research, vision |
dual-gpu |
app + ollama + vllm + vision + searxng | GPU 0 = Ollama, GPU 1 = vLLM |
First-Run Wizard
On first launch the setup wizard walks through seven steps:
- Hardware — detects NVIDIA GPUs and recommends a profile
- Tier — choose free, paid, or premium (or use
dev_tier_overridefor local testing) - Identity — name, email, phone, LinkedIn, career summary
- Resume — upload a PDF/DOCX for LLM parsing, or use the guided form builder
- Inference — configure LLM backends and API keys
- Search — job titles, locations, boards, keywords, blocklist
- Integrations — optional cloud storage, calendar, and notification services
Wizard state is saved after each step — a crash or browser close resumes where you left off. Re-enter the wizard any time via Settings → Developer → Reset wizard.
Features
| Feature | Tier |
|---|---|
| Job discovery (JobSpy + custom boards) | Free |
| Resume keyword matching | Free |
| Cover letter generation | Paid |
| Company research briefs | Paid |
| Interview prep & practice Q&A | Paid |
| Email sync & auto-classification | Paid |
| Survey assistant (culture-fit Q&A) | Paid |
| Integration connectors (Notion, Airtable, Google Sheets, etc.) | Paid |
| Calendar sync (Google, Apple) | Paid |
| Cover letter model fine-tuning | Premium |
| Multi-user support | Premium |
Email Sync
Monitors your inbox for job-related emails and automatically updates job stages (interview requests, rejections, survey links, offers).
Configure in Settings → Email. Requires IMAP access and, for Gmail, an App Password.
Integrations
Connect external services in Settings → Integrations:
- Job tracking: Notion, Airtable, Google Sheets
- Document storage: Google Drive, Dropbox, OneDrive, MEGA, Nextcloud
- Calendar: Google Calendar, Apple Calendar (CalDAV)
- Notifications: Slack, Discord (webhook), Home Assistant
Developer Docs
Full documentation at: https://docs.circuitforge.io/peregrine
License
Core discovery pipeline: MIT AI features (cover letter generation, company research, interview prep, UI): BSL 1.1
© 2026 Circuit Forge LLC