AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Browser Automation/
Jobs_Applier_AI_Agent_AIHawk
Jobs_Applier_AI_Agent_AIHawk logo

Jobs_Applier_AI_Agent_AIHawk

Active·★ 32.6k·MIT·Updated 2026-11-17
★ Most Popular

AIHawk is a terminal job-search assistant that uses a resume to plan searches, shortlist postings and work through application forms in a visible browser. It is relevant to users who will review fit explanations and form contents rather than assume a job match or successful send. We tested package 1.0.0 at a fixed commit with Python 3.12.13. Selected modules ran against invented postings, synthetic CVs and temporary files. No personal information, real employer site, mailbox, browser engine or model gateway was used.

Eleven checks covered local Parquet search, SQLite persistence, resume text and scripted submission states. Keyword, location and exclusion filters worked on the five-row index, while old and unrelated jobs were excluded and duplicate company/title postings were merged. Text and a minimal DOCX were readable; content below fifty characters was refused. Rediscovering a job ID preserved its existing unconfirmed attempt state. CSV export retained uncertainty and wrote formula-like fields as text. These results concern deterministic filtering and record handling, not the accuracy of model-generated search plans or suitability scores.

Using a fake browser and preset gateway verdicts, the actual post-submit function distinguished submitted, unconfirmed and refused. A fake click error followed by verification failure remained unconfirmed, without a second fake click. This does not establish real-site success. The sending classifier depends on wording and treated Continue as a step even with a submit type, so it is not a strict authorization boundary. The documented live workflow sends CV and page content to a model gateway. Start with local search and records, then separately assess the chosen site, submitted content and data handling before using personal material.

Read the full review, verification scope and sources →

Hands-on tested · Tested on 2026-11-05 with 1.0.0; commit e74f532b83f0a376694309c86e1636fb6a6dd516 (local data and simulated submission states only).

Setup: macOS arm64, CPython 3.12.13; isolated dependencies, synthetic rows/CVs and temporary databases; Python socket connections blocked

Commands run

<venv>/bin/python doc/review-fixtures/stock-jobs-20261105/verify.py --sources <source-parent> --output /tmp/stock-jobs-results.json

What we saw

  • Eleven local checks passed on five invented postings, synthetic TXT/DOCX files and temporary SQLite.
  • Rediscovery preserved unconfirmed status; CSV kept uncertainty and formula-like fields as text.
  • Fake-browser/scripted-verdict paths mapped submitted/unknown/rejected distinctly. No real send, browser, personal CV or model call.

Data as of 2026-11-12.

License
MIT
Latest release
jobs-latest · 2026-11-04
Last commit
2026-11-11
Contributors
1
Forks
4,751
Open issues and PRs
2
First published
2024-08-04

Source: GitHub, npm and PyPI public APIs.

#ai-agent#browser-automation#job-search#job-application#resume#python#terminal-ui#llm
$ Install
$ pipx install git+https://github.com/feder-cr/Jobs_Applier_AI_Agent_AIHawk
↗ Visit site★ GitHub
01

Features

01Resume-based job search and shortlisting
02Terminal interface with job scores and gaps
03Visible-browser form assistance and submission records
02

Why choose it

+Local job filters excluded old and unrelated postings and merged duplicate company/title results.
+Rediscovery retained existing attempt status; CSV preserved uncertainty and neutralized formula-like fields.
+Simulated post-click verification failure remained unconfirmed without a duplicate fake click.
03

Trade-offs

!Scripted browser and model verdicts do not establish real application success or fit accuracy.
!Sending-control detection depends on wording and treats Continue as a step.
!The live workflow sends CV and page content to a gateway; personal-data handling requires review.
05

Maintenance check

ActiveChecked: 2026-11-12
Last commit
2026-11-11
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
jobs-20261108-084120 (2026-11-08)
Open issues
2
Recent issues with at least one comment
—
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 28, 273, 58, 0, 0, 124, 61

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #1457 Power-user offer: real daily outreach volume, feedback, and a case study1 comments · 2026-10-20
  • #1452 Apple ID 账号购买0 comments · 2026-10-14

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You want local shortlist and attempt records that can be inspected.
  • You will review content and validate the actual target-site workflow.
Look elsewhere if
  • You need a proven automated application success rate.
  • You require entirely local processing or a strict sending authorization boundary.
06

Compatibility

Python
3.11+
Verified via docs
Browser automation
Visible browser with site plugins
Verified via docs
07

Quick start

1
$ pipx install git+https://github.com/feder-cr/Jobs_Applier_AI_Agent_AIHawk
08

Use cases

↳Finding positions related to resume experience
↳Reviewing role fit before selecting applications
↳Preparing application materials and reviewing send records
09

Alternatives

⚡Top VS:
VSbrowser-harness★19.1k→VSGenericAgent★14.4k→VSparlant★18.3k→VSindex★2.4k→
browser-harness logo
browser-harness★ 19.1k
Let Claude Code, Codex or Cursor use your real Chrome, logged in as you. One prompt to set up. Open source, MIT.
VSCompare→
GenericAgent logo
GenericAgent★ 14.4k
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
VSCompare→
parlant logo
parlant★ 18.3k
Parlant is an open platform for building customer-facing chat agents with AI. Describe how the agent should behave, and your coding agent implements it for you.
VSCompare→
index logo
index★ 2.4k
The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web
VSCompare→
Scrapling logo
Scrapling★ 103.9k
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
VSCompare→
nanobrowser logo
nanobrowser★ 14.3k
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
VSCompare→
open-cuak logo
open-cuak★ 391
Reliable Automation Agents at Scale
open-codex-browser-use logo
open-codex-browser-use★ 425
👾 Open Browser Use – Open-Source Alternative to Codex Browser Use
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06Compatibility07Quick start08Use cases09Alternatives
feder-cr /
Jobs_Applier_AI_Agent
↗

A terminal job assistant with inspectable application attempts

32.6k4.8kMIT
Last commit1d ago
StatusActive
CategoryBrowser Automation
Contributors1
Latest releasejobs-latest
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.