Show HN: NextRole – multi-agent resume tailoring and interview prep

NextRole, a multi-agent system for resume tailoring and interview prep, launched on Show HN. The open-source tool uses specialized AI agents to research companies, rewrite resumes, and generate interview prep materials, running entirely in Docker. It aims to automate the tedious process of preparing for job interviews.

Upload your CV + a job description. Get a tailored resume PDF, a researched interview-prep doc, and a day-of battlecard cheat sheet — built by a multi-agent system with long-term memory. Preparing for an interview takes hours of tedious resume tailoring and company research. NextRole automates the heavy lifting. Hand it your current CV and a target Job Description or just a JD URL — whether you're applying externally or angling for an internal move — and a team of specialized AI agents researches the company, rewrites your resume to fit, coaches you round-by-round, and prints a cheat sheet for the day of. - 📄 Tailored resume → PDF — your experience rewritten against the exact JD + company research, rendered with editable & re-renderable . rendercv - 🔍 Deep company & role recon — live web research distilled into a match analysis. - 🎯 Structured interview prep — a self-introduction plus per-round STAR stories mapped to the role. - ⚡ Day-of battlecard — a one-page-per-round PDF cheat sheet for the final high-pressure review. - 🗓️ Time-boxed prep plans — a study plan that fits 1 month, 2 weeks, or just 3 hours. - 🔗 Paste a JD URL — point it at a careers page; it extracts and processes the posting for you. - 💬 Iterate by chatting — "add a 4th round", "add React to my skills" — streaming multi-turn edits, with the right agent owning each file. - 🗂️ Built-in workspace — upload, preview PDF / MD / YAML / JSON / code , print-to-PDF, and swap the LLM at runtime. next-role-demo.mp4 Watch the full walkthrough in HD on YouTube » https://youtu.be/7RzDYpmfOyA The whole stack — frontend, backend, Postgres, Redis — runs in Docker. 1. Clone & configure git clone https://github.com/tam159/next-role.git cd next-role cp .env.example .env then fill in your API keys see table below 2. Launch everything docker compose up -d 3. Find your host ports set in .env, vary per machine docker ps read the 0.0.0.0:<host - ... mappings 4. Open the app Frontend UI → http://localhost:<FRONTEND LOCAL PORT / Backend API docs → http://localhost:<LANGGRAPH LOCAL PORT /docs 💡 Pick your LLM in the app.Open the in-appConfigurationdialog to set the main agent and subagent models — no rebuild needed. SeeLLM configurationbelow for recommended models and free / local options. Environment variables — what to put in .env | Variable | Required | Purpose | |---|---|---| OPENAI API KEY | ✅ | Default main + subagent models | TAVILY API KEY | ✅ | Web research hiring-recon | LLAMA CLOUD API KEY | ✅ | Document parsing LlamaParse | POSTGRES PASSWORD | ✅ | Local Postgres password | ANTHROPIC API KEY / GOOGLE API KEY | ⬜ | Alternative providers swap at runtime | OPENAI API BASE | ⬜ | Self-hosted / Azure / LM Studio endpoint | AWS ACCESS KEY ID / AWS SECRET ACCESS KEY / AWS DEFAULT REGION | ⬜ | AWS Bedrock models | LANGCHAIN API KEY + LANGCHAIN TRACING V2=true | ⬜ | LangSmith tracing recommended | FRONTEND LOCAL PORT / LANGGRAPH LOCAL PORT / POSTGRES LOCAL PORT / REDIS LOCAL PORT | preset | Host port mappings | Secrets live only in .env gitignored ; gitleaks runs on every commit. LLM configuration — pick your models, run it for free or local Models are swappable at runtime — no rebuild. Open the in-app Configuration dialog and set Main agent / Subagents to a <provider :<model string e.g. anthropic:claude-sonnet-4.6 ; leave blank to use the defaults. Settings persist in your browser's local storage. Recommended: Claude Sonnet 4.x, GPT-5.x, or Gemini 3.x — e.g. anthropic:claude-sonnet-4.6 , openai:gpt-5.4 , google genai:gemini-3.5-flash . Run it for free or fully local: Tavily and LlamaCloud both include a generous monthly free tier — plenty for local use. Google AI Studio offers a free tier for Gemini flash / lite models. Fully local — point OPENAI API BASE at LM Studio https://lmstudio.ai/ or Ollama https://ollama.com/ both expose an OpenAI-compatible API and fill your local model in the UI. Output quality tracks the model you pick — smaller local models trade some quality for zero cost. Dev workflow — hot reload, restart, rebuild, stop Code edits hot-reload in both containers — just save the file. Add a frontend dep: pnpm --dir frontend add <pkg → docker compose restart frontend Add a backend dep: uv add <pkg → docker compose up -d --build backend Change .env : docker compose restart <service Stop: docker compose down add -v to wipe the DB & Redis volumes NextRole is a supervisor agent orchestrating three specialist subagents on LangGraph + DeepAgents. The main agent handles intake, document processing, and the final battlecard; it delegates research, resume tailoring, and interview coaching to declarative subagents defined in subagents.yaml , each with its own model, tools, and skills . A five-stage pipeline. Stage 4 runs the resume tailor and interview coach in parallel ; Stage 6 routes follow-up edits to whichever agent owns the target file. Stage-by-stage detail Intake — the agent asks for your CV, the JD file, URL, or pasted text , your prep timeline, and any extra context. Process documents — uploads are parsed to markdown via LlamaParse parse document ; JD URLs are pulled via Tavily extract jd . Results land in /processed/ , alongside a persisted intake note. Research — the hiring-recon subagent gathers company + role intel and a match analysis → /research/<resume /<jd .md . Tailor & coach parallel — resume-tailor rewrites the CV as a rendercv YAML and renders a PDF; interview-coach writes a structured prep doc self-intro + per-round STAR stories . Battlecard — the main agent assembles a one-page-per-round JSON and renders it to a day-of PDF via WeasyPrint. Multi-turn updates — ask for changes in chat; the owning agent reads the existing file, preserves everything you didn't name, and re-renders. The full procedure file layout, update routing, source-of-truth conventions lives in . Per-feature design docs are in backend/app/career agent/README.md . docs/prd/ The DeepAgents stack — an agent defined by filesystem primitives The agent's behavior is configured by files, not hardcoded — making it easy to read, diff, and extend: | Primitive | Where | Role | When loaded | |---|---|---|---| Memory | AGENTS.md | Per-stage procedure manual semantic memory | Always system prompt | Skills | skills/<consumer /<name /SKILL.md | Task workflows procedural memory | On demand, per consumer | Subagents | subagents.yaml | Specialist delegates → the task tool | Always | Tools | tools.py + DeepAgents built-ins | parse document , extract jd , render battlecard pdf , prepare render settings , list files , overwrite file , plus read/write/edit file , ls/glob/grep , execute | — | Filesystem | CompositeBackend | Routes virtual paths to the right store see below | — | Middleware | middleware.py | ModelOverrideMiddleware runtime LLM swap + UtcDatetimeMiddleware | — | Subagents only receive the tools they opt into in YAML — tool whitelisting keeps interview-coach , for example, from inheriting the main agent's full toolset. Memory & storage architecture A single CompositeBackend gives the agent one virtual filesystem while routing each path prefix to the right physical store — Postgres for text artifacts, disk for binaries and render outputs, and a shell backend that translates virtual paths to real ones before running commands like rendercv render . flowchart LR Agent "Agent filesystem tools<br/ read file · write file · edit file<br/ ls · glob · grep · execute" CB{{"CompositeBackend<br/ routes virtual paths"}} Agent -- CB subgraph Shell "VirtualPathShellBackend · default route" SH "rewrites /virtual/path → on-disk path<br/ before subprocess.run<br/ e.g. rendercv render /tailored resume/... " end subgraph Store "StoreBackend · Postgres + pgvector" ST "/memory/ · /processed/ · /research/<br/ /interview coach/<br/ /large tool results/ · /workspace/" end subgraph Disk "FilesystemBackend · disk binaries + renders " DK "/upload/ · /tailored resume/<br/ /render intermediate/<br/ /interview battlecard/" end CB -- |default| Shell CB -- |KV routes| Store CB -- |binary + PDF routes| Disk Sem "Semantic memory · AGENTS.md" -. loaded into system prompt .- Agent Proc "Procedural memory · skills/ /SKILL.md" -. loaded on demand .- Agent Work "Working memory · LangGraph thread" -. drives .- Agent Store --- Epi "Episodic memory · persisted artifacts<br/ incl. /memory/ auto-memory " Disk --- Epi Mapped to memory types: Working memory — the live LangGraph conversation thread. Semantic memory — AGENTS.md , always in the system prompt. Procedural memory — skills/ /SKILL.md , loaded on demand. Episodic memory — persisted artifacts in Postgres + disk, including auto-memory : standing preferences saved to the /memory/ route and auto-applied across sessions. Tech stack | Layer | Stack | |---|---| Backend | Python 3.13 · LangChain v1 · LangGraph 1.x · DeepAgents 0.6 · uv · served on langchain/langgraph-api:3.13 | Agent I/O | Tavily web search · LlamaParse / LlamaCloud document parsing · rendercv resume → PDF · WeasyPrint battlecard → PDF | Frontend | Next.js 16 · React 19 · TypeScript · Tailwind · pnpm · @langchain/react v2 useStream | Data | PostgreSQL 18 + pgvector · Redis 8 | Infra | Docker Compose frontend · backend · postgres · redis | Observability | LangSmith | Expose the agent — MCP & A2A Because NextRole runs on the LangGraph Agent Server , the career agent assistant is also reachable by other tools and agents — no extra code: MCP — exposed as Model Context Protocol tools at Streamable HTTP , usable by any MCP-compliant client. → /mcp docs https://docs.langchain.com/langsmith/server-mcp A2A — Google's Agent2Agent protocol at JSON-RPC 2.0; /a2a/{assistant id} message/send + message/stream . → docs https://docs.langchain.com/langsmith/server-a2a - The full server API is browsable at the endpoint of your deployment. /docs Observability — LangSmith tracing Set LANGCHAIN API KEY and LANGCHAIN TRACING V2=true in .env , and every run — each LLM call, tool call, and nested subagent — is traced at smith.langchain.com https://smith.langchain.com/ under the LANGCHAIN PROJECT you configure. Optional, but invaluable for debugging the multi-agent flow. - 💤 "Auto-dream" consolidation — sleep-time compaction that prunes stale notes and merges insights into durable memory. - 📦 Remote sandboxes — swap LocalShellBackend for an isolated remote sandbox e.g. Daytona https://www.daytona.io/ so render/shell steps are safe for multi-tenant use. - 📊 Agent evaluation — LangSmith evals over the workflow the @pytest.mark.eval marker is already reserved . - 🎨 Enhanced UI — richer artifact editing, diff views, and inline regeneration. - 🔌 MCP / A2A examples — sample integrations driving career agent from external agents and IDEs. - 🧵 Per-thread / multi-user scoping — namespace artifacts per user instead of the current global layout. - 🌐 More sources & ATS-aware tailoring — pluggable retrievers + keyword/ATS optimization passes. NextRole is built for local, single-user, trusted usetoday. - 🔒 Local shell execution — VirtualPathShellBackend runs render commands via subprocess on the host. Safe locally; not hardened for multi-tenant production needs sandboxing — see roadmap . - 👤 Global file scoping — uploads and artifacts share one filesystem layout; re-uploading a filename overwrites. No per-user isolation yet. - 🧪 LLM evals deferred — current tests are unit + local-DB integration; automated quality evals aren't wired up yet. - 🧠 Personalization is preferences-only — the agent persists and auto-applies the preferences you state across sessions, but doesn't yet infer your style/history on its own or consolidate memory over time see roadmap roadmap . - ⏱️ Latency — a full run makes several LLM and tool calls across multiple agents; expect minutes, not seconds. PRs and issues are welcome Start with — it walks through the fork → PR workflow, local setup, the CI quality gate pre-commit + backend tests , testing, and conventions. Stack-specific details live in CONTRIBUTING.md and /tam159/next-role/blob/main/backend/CLAUDE.md backend/CLAUDE.md ; commits follow /tam159/next-role/blob/main/frontend/CLAUDE.md frontend/CLAUDE.md Conventional Commits https://www.conventionalcommits.org/ . New here? Issues labelled good first issue https://github.com/tam159/next-role/labels/good%20first%20issue are a gentle place to start, and questions are welcome in Discussions https://github.com/tam159/next-role/discussions . MIT /tam159/next-role/blob/main/LICENSE © 2026 Tam Nguyen Built on DeepAgents https://github.com/langchain-ai/deepagents , LangChain / LangGraph / LangSmith https://github.com/langchain-ai , rendercv https://github.com/rendercv/rendercv , WeasyPrint https://github.com/Kozea/WeasyPrint , Tavily https://tavily.com/ , and LlamaIndex / LlamaParse https://github.com/run-llama/llama index .