#77th of 48 in Agent platforms
resume-matcher
Tailors resumes and cover letters to job descriptions using local or hosted LLMs
- Stars
- 28.8k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
26,003 on 27 Mar 202628,843 on 23 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Resume Matcher takes a master resume (PDF or DOCX) and a pasted job description, then generates a tailored resume, cover letter and optional interview prep. It scores the match, highlights keywords, and exports PDFs from 10 templates through headless Chromium. The backend is FastAPI with LiteLLM, the frontend is Next.js, and storage is SQLite by default with optional PostgreSQL.
Who it is for: Job seekers who want to self-host resume tailoring with local or API LLMs
Ranked among open-source alternatives to Copilot Studio (#7 of 10).
Strengths
- Works with Ollama locally and with OpenAI, Anthropic, Gemini, OpenRouter, DeepSeek and Groq
- SQLite by default, so no separate database is required
- Tailoring queue processes several job descriptions in the background and resumes after restart
- Multi-arch Docker images (amd64, arm64) serve app and API on port 3000
Weaknesses
- Manual setup needs Python 3.13+, Node.js 24+ and uv
- Claude CLI and ChatGPT sign-in providers do not work in the default Docker setup
- Subscription-based providers depend on unofficial third-party access and may stop working
- RAM and GPU requirements are not stated
What it needs
- GPU optional
- Docker + Compose
- Needs Python 3.13+, Node.js 24+, uv, Playwright Chromium, SQLite or PostgreSQL
- Models: Ollama, OpenAI, Anthropic, Google Gemini, OpenRouter
- port 3000
Quick answers
Is resume-matcher open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run resume-matcher with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does resume-matcher need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Agent platforms
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 94 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 94 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 93 out of 100 |
| #4 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |
| #5 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 88 out of 100 |