pyr0ball
0d6ddd35cf
- Rename user-facing env var CF_ORCH_URL → GPU_SERVER_URL with full backward-compat alias (closes #116). Priority chain: GPU_SERVER_URL → CF_ORCH_URL → orch.circuitforge.tech when CF_LICENSE_KEY present. Write-back to os.environ[CF_ORCH_URL] keeps all downstream callers unchanged. - Add four task-routed llm.yaml backends (cf_cover_letter, cf_ats_rewrite, cf_job_research, cf_interview_prep) using cf_orch.product + cf_orch.task. Coordinator resolves model/node from assignments.yaml (closes #115). - Update compose.yml, compose.cloud.yml, compose.test-cfcore.yml, .env.example to use GPU_SERVER_URL as primary documented var. |
||
|---|---|---|
| .forgejo/workflows | ||
| .gitea/ISSUE_TEMPLATE | ||
| .githooks | ||
| .github | ||
| app | ||
| config | ||
| data | ||
| demo | ||
| docker | ||
| docs | ||
| migrations | ||
| resume_matcher/apps/backend/app | ||
| scrapers | ||
| scripts | ||
| tests | ||
| tools | ||
| web | ||
| .cliff.toml | ||
| .dockerignore | ||
| .env.e2e.example | ||
| .env.example | ||
| .gitignore | ||
| .gitleaks.toml | ||
| CHANGELOG.md | ||
| compose.cloud.yml | ||
| compose.demo.yml | ||
| compose.gpu.yml | ||
| compose.podman-gpu.yml | ||
| compose.test-cfcore.yml | ||
| compose.yml | ||
| CONTRIBUTING.md | ||
| dev-api.py | ||
| dev_api.py | ||
| Dockerfile | ||
| Dockerfile.cfcore | ||
| Dockerfile.finetune | ||
| environment.yml | ||
| HANDOFF-xanderland.md | ||
| install.sh | ||
| LICENSE-BSL | ||
| LICENSE-MIT | ||
| Makefile | ||
| manage.sh | ||
| mkdocs.yml | ||
| podman-standalone.sh | ||
| PRIVACY.md | ||
| pytest.ini | ||
| README.md | ||
| requirements.txt | ||
| SECURITY.md | ||
Peregrine
Job search pipeline — by Circuit Forge LLC
AI for the tasks the system made hard on purpose.
Live Demo — no account required, nothing saved | Docs | Issues
Primary development happens at git.opensourcesolarpunk.com/Circuit-Forge/peregrine. GitHub and Codeberg are push mirrors. Issues and PRs are welcome on any platform.
 |
 |
 |
 |
Why Peregrine?
Job search is a second job nobody hired you for. ATS (applicant tracking system) filters designed to reject. Boards that show the same listing eight times. Cover letter number forty-seven for a role that might already be filled. Hours of prep for a phone screen that lasts twelve minutes.
- Handles the full pipeline. Discover, filter, match, draft, track — one tool, one database, no duct tape.
- LLM is optional and local-first. Discovery and tracking work with no LLM at all. When you do configure one, it runs on your hardware by default. Cloud inference is a fallback, not the default path.
- Ghost-post detection baked in. Listings that have been open too long or look like sourcing traps get flagged before you spend time on them.
- Human approval at every step. LLM drafts cover letters and research briefs; you approve before anything goes anywhere. Peregrine never submits an application on your behalf.
- Privacy · Safety · Accessibility are architectural constraints, not aspirational copy. No PII (personally identifiable information) logging, no behavioral profiling, no dark patterns.
Quick Start
One-line install:
bash <(curl -fsSL https://git.opensourcesolarpunk.com/Circuit-Forge/peregrine/raw/branch/main/install.sh)
Or clone and run manually:
git clone https://git.opensourcesolarpunk.com/Circuit-Forge/peregrine
cd peregrine
./manage.sh setup
./manage.sh start
Open http://localhost:8502 — the setup wizard walks you through the rest.
macOS / Apple Silicon: install Ollama natively via Homebrew before starting for Metal GPU-accelerated inference.
install.shhandles this automatically. Windows: use WSL2 with Ubuntu.
Inference profiles
./manage.sh start # remote — no GPU; LLM calls go to Anthropic / OpenAI
./manage.sh start --profile cpu # local Ollama on CPU (or Metal via native Ollama on macOS)
./manage.sh start --profile single-gpu # Ollama + vision on GPU 0 (NVIDIA only)
./manage.sh start --profile dual-gpu # Ollama + vLLM on two NVIDIA GPUs
Features
| Feature | Tier |
|---|---|
| Job discovery — LinkedIn, Indeed, Glassdoor, Adzuna, The Ladders | Free |
| Ghost-post detection | Free |
| Resume keyword matching and gap analysis | Free |
| Document storage sync (Google Drive, Dropbox, OneDrive, Nextcloud) | Free |
| Webhook notifications (Discord, Home Assistant) | Free |
| Vue 3 SPA — full UI with onboarding wizard, job board, apply workspace, interview kanban | Free |
| Cover letter generation | Free with LLM ¹ |
| Company research briefs | Free with LLM ¹ |
| Interview prep and practice Q&A | Free with LLM ¹ |
| Survey assistant (culture-fit Q&A, screenshot analysis) | Free with LLM ¹ |
| Managed cloud LLM (no API key needed) | Paid |
| Email sync and auto-classification | Paid |
| Job tracking integrations (Notion, Airtable, Google Sheets) | Paid |
| Calendar sync (Google, Apple) | Paid |
| Slack notifications | Paid |
| CircuitForge shared cover-letter model | Paid |
| Voice guidelines (custom writing style and tone) | Premium with LLM ¹ |
| Cover letter model fine-tuning — your writing, your model | Premium |
| Multi-user support | Premium |
| Human-in-the-loop operator (CAPTCHAs, phone calls, wet signatures) | Ultra |
¹ BYOK (bring your own key) unlock: configure any LLM backend — a local Ollama or vLLM instance, or your own API key (Anthropic, OpenAI-compatible) — and all "Free with LLM" and "Premium with LLM" features unlock at no charge.
What Peregrine does not do
Peregrine does not submit job applications for you. You still click apply on the employer's site.
This is intentional. Automated mass-applying is a bad experience for everyone and a trust violation with employers who posted a real role. The submit button is yours. The rest of the grind is ours.
Stack
| Layer | Technology |
|---|---|
| Frontend | Vue 3 SPA (Vite) |
| Backend | FastAPI + Python |
| Database | SQLite (local, per-user) |
| Job scraping | JobSpy + custom board scrapers |
| LLM inference | Ollama, vLLM, Anthropic, OpenAI-compatible — configurable fallback chain |
| Vision | moondream2 (survey screenshot analysis) |
| Container | Docker / Podman |
manage.sh reference
./manage.sh setup Install Docker/Podman + NVIDIA toolkit
./manage.sh start [--profile P] Preflight check then start services
./manage.sh stop Stop all services
./manage.sh restart Restart all services
./manage.sh status Show running containers
./manage.sh logs [service] Tail logs (default: app)
./manage.sh update Pull latest images and rebuild app container
./manage.sh test Run test suite
./manage.sh prepare-training Scan docs for cover letters — outputs training JSONL
./manage.sh finetune Run LoRA fine-tune (requires single-gpu profile or higher)
./manage.sh open Open the web UI in your browser
Documentation
Full docs at docs.circuitforge.tech/peregrine
Bug reports and feature requests: Forgejo issues
Contributing
Contributions are welcome. The discovery pipeline — scrapers, board integrations, matching logic — is MIT-licensed. Fork it, extend it, send PRs. AI features are BSL 1.1. See the contributing guide for conventions.
License
Peregrine uses a split license:
| Component | License |
|---|---|
| Discovery pipeline — scrapers, matching, tracking | MIT |
| LLM features — cover letter generation, company research, interview prep, survey assistant, fine-tuning | BSL 1.1 — free for personal non-commercial self-hosting; commercial use or SaaS re-hosting requires a paid license; converts to MIT after four years |
Fine-tuned model weights are proprietary and per-user — not redistributable.
© 2026 Circuit Forge LLC