CareerBot

Open-source Python + MCP toolkit

Move faster.
Keep the evidence.

CareerBot scores job fit, prepares verified application artifacts, preserves immutable snapshots, and stops at the boundaries that need a human.

Clone and run Explore the repository
  • Verified claims only
  • Bounded sessions
  • Human approval gates
Terminal

# Clone the open-source project

$ git clone https://github.com/Sai21112000/CareerBot.git $ cd CareerBot $ uv sync --extra dev
Ready for a bounded dry run
Python 3.12Typed runtime
12 MCP toolsFocused interfaces
SHA-256Artifact manifests
MITOpen source

Capabilities

A clear path from job input to review-ready package.

Each module does one job and leaves behind inspectable state, so a workflow can stop, resume, or hand control back without losing context.

01

Normalize and rank

Deduplicate supplied jobs and prioritize the bounded input set before model calls.

Local first
02

Score against evidence

Compare requirements with a private, hash-verified Master CV using xAI.

CV-grounded
03

Prepare artifacts

Draft positioning, LaTeX resumes, and concise letters from verified facts.

ATS checked
04

Preserve snapshots

Save immutable application packages with file sizes and SHA-256 manifests.

Auditable
05

Track without guessing

Record prepared and submitted state locally, with optional Airtable tracking and explicit confirmation evidence.

Idempotent

Architecture

Narrow tools. Private sources. Explicit boundaries.

Use the CLI directly, connect Cursor over stdio MCP, or expose a protected remote endpoint through your own infrastructure.

CareerBot clients, runtime modules, integrations, and private local data

Safety by design

Automation has a boundary. CareerBot makes it visible.

The project ships preparation, policy assessment, and handoff logic—not a default job-board auto-submit connector.

01

No hidden experienceGenerated claims stay inside verified CV evidence.

02

No bypassesCAPTCHA, MFA, identity, consent, and declarations require a handoff.

03

No unbounded runsJob, application, and elapsed-time limits are configurable.

CareerBot evidence workflow and policy-controlled handoff

Model Context Protocol

Use CareerBot where you already work.

Twelve scoped tools cover strategy, discovery, scoring, artifact generation, snapshots, tracking, and submission policy.

Read the MCP setup
score_job search_jobs tailor_resume verify_snapshot assess_submission track_application consult_career_positioning

Quick start

Clone it. Keep your private data private.

Start with fictional inputs and a dry-run profile. Private resumes, credentials, application records, and snapshots remain in ignored local paths.

1

Clone the repositoryGet the code directly from GitHub.

2

Install dependenciesUse uv with Python 3.12 or newer.

3

Create private filesCopy the safe examples and replace verified placeholders.

4

Run locallyInspect the CLI before adding external integrations.

bash 
# Clone CareerBot
git clone https://github.com/Sai21112000/CareerBot.git
cd CareerBot

# Install and create private configuration
uv sync --extra dev
cp .env.example .env
cp AGENTS.md.example AGENTS.md
cp data/master_resume.tex.example data/master_resume.tex

# Inspect the local CLI
uv run careerbot --help

Build your bounded workflow

Open source. Inspectable. Ready to clone.

Get CareerBot on GitHub git clone …/CareerBot.git