Freelancers using OllamaFreelancers using Ollama
ProjectsPeople
Haris Iftikhar's avatar
Haris Iftikhar
Austin, USA
Full-Stack AI Engineer for Web Apps & Automations
$10k+
Earned
9x
Hired
4.9
Rating
50
Followers
Full-Stack AI Engineer for Web Apps & Automations
Cover image for Development of AI Educational Platform for Belto.World
Development of AI Educational Platform for Belto.World
1
15
Cover image for AI Meeting Tracker – Intelligent Meeting Summaries & Insights
AI Meeting Tracker – Intelligent Meeting Summaries & Insights
2
38
Cover image for Clinic Caller – AI-Enabled Patient Communication Platform
Clinic Caller – AI-Enabled Patient Communication Platform
1
32
Cover image for Roam Epic – Travel Blog & Social Media Platform
Roam Epic – Travel Blog & Social Media Platform
0
14
Ollama(1)
John L's avatar
John L
Matteson, USA
Distributed AI | Soverign AI | Local First
Distributed AI | Soverign AI | Local First
Cover image for BenevolentJoker-JohnL/Sheppard
BenevolentJoker-JohnL/Sheppard
1
8
Cover image for The Human Matrix: Break the System
The Human Matrix: Break the System
1
6
Cover image for BenevolentJoker-JohnL/FlockParser
BenevolentJoker-JohnL/FlockParser
0
9
Placeholder project card media
View more →
Ollama(3)
Yossef Ayman Zedan's avatar
Yossef Ayman Zedan
Cairo, Egypt
I build AI agents that automate business workflows
New to Contra
I build AI agents that automate business workflows
Cover image for LeadBot is a B2B lead
LeadBot is a B2B lead automation platform I built that turns raw scraped LinkedIn data into scored, tiered leads with personalized outreach ready to send. It extracts company and profile links from raw page data, runs each lead through a scoring pipeline that checks hiring signals and applicant volume before spending on deeper enrichment, then classifies leads as Cold, Warm, or Hot with transparent reasoning behind every score. For qualified leads, it generates personalized connection notes and follow-up messages based on the specific role or signal that made them worth reaching out to, not generic templates. Built with LangGraph orchestration and Ollama for the scoring and message generation, with every lead persisted so nothing gets processed twice.
0
19
Cover image for OneRecruiter is an AI-powered candidate
OneRecruiter is an AI-powered candidate screening tool I built for small staffing agencies, where AI screening rejects good candidates and consultants can't afford to look like a black box. Every criterion in a role's rubric is scored independently with a transparent, auditable rationale, so recruiters see exactly why a candidate scored 90% instead of trusting a mystery number. The standout feature is candidate pooling: agencies upload their CV database once and it stays matched against every future job, so a candidate sourced for one role automatically surfaces for the next relevant opening. Validated it end-to-end with a real staffing agency client, running a live CAD Designer search against 12 candidates with synthetic test data before their real screening.
0
62
Cover image for InvoiqAI is an AP invoice
InvoiqAI is an AP invoice automation tool I built that reads invoices, purchase orders, and delivery receipts, cross-checks them against each other, and routes approvals automatically, so AP teams stop manually keying numbers and stop paying invoices nobody actually verified. It runs full three-way matching on every document, flags price or quantity mismatches with plain-English reasoning, and catches duplicate invoices before they get paid twice. Approval rules route small invoices to auto-approve and larger ones to the right person, so nothing sits in a queue waiting on a human unless it actually needs one. Tested across 85+ real documents with a 96.5% extraction pass rate.
0
32
Cover image for Contract Control Center is a
Contract Control Center is a local-first contract analysis tool I built that turns a folder of contracts into a full risk pack: a portfolio table, a renewal and notice calendar, CFO-ready review questions, and exportable Excel, PDF, and calendar files. Every extracted value traces back to the exact quoted sentence and page it came from, so nothing is guessed. It reads the full document rather than sampling it, catches auto-renewal traps and uncapped liability clauses, and turns messy payment schedules and notice periods into a calendar you can actually act on before a deadline passes. It runs entirely on your machine with a local AI model, so contracts never have to leave your network.
0
26
Ollama(3)
Usama Idrees's avatar
Usama Idrees
Islamabad, Pakistan
Enterprise Cloud · DevOps · AI/ML · Email · Marketing Expert
$10k+
Earned
13x
Hired
4.4
Rating
41
Followers
Enterprise Cloud · DevOps · AI/ML · Email · Marketing Expert
Cover image for I’m Usama Idrees, IT &
I’m Usama Idrees, IT & AI Specialist based in Islamabad, Pakistan. Thrilled to be part of this amazing community and to connect with talented Professionals from around the world! 🚀 A little about me: What I do: I lead tech and product strategy, focusing on building innovative solutions that empower businesses and individuals. Passion: Creativity meets technology — I love turning ideas into impactful products. Looking for: Collaborations with designers, developers, and creative minds who want to build something extraordinary. Excited to learn, share, and grow together here. If you’re working on something cool or looking for a tech partner, let’s connect! 💡 What’s your current creative project? Drop it below — I’d love to check it out. 👇
2
30
792
Cover image for IT/AI Infrastructure Support
$501 earned
IT/AI Infrastructure Support
2
53
Cover image for Email Ticketing System Optimization with Trello + SendBoard
$750 earned
Email Ticketing System Optimization with Trello + SendBoard
2
68
Cover image for Full-Stack SEO Framework for B2B SaaS Company
Full-Stack SEO Framework for B2B SaaS Company
1
19
Ollama(1)
Tim Green's avatar
Tim Green
proNelson BB9, UK
Principal Engineer, PHP Backend specialist, Article Writer
16
Followers
Principal Engineer, PHP Backend specialist, Article Writer
Cover image for Ollama MCP Server Development
Ollama MCP Server Development
0
4
Cover image for https://github.com/rawveg/ollama-mcp
https://github.com/rawveg/ollama-mcp
0
75
Cover image for Today I've launched the next
Today I've launched the next evolution of my non-fiction written work. For just over a year I've been writing long-form daily articles about Technology, Governance and the Human cost of the things we build at smarterarticles.co.uk (https://smarterarticles.co.uk) Six weeks ago I launched a podcast, taking one of my published articles, and reworking it for the podcast format, with a new episode weekly. Today I launched the accompanying website: smarterarticles.fm (https://smarterarticles.fm) My spec was simple:- 1. Keep it simple, and minimalistic. My articles are published on a simple site, headlines, and content, and nothing more. I wanted to keep that simplicity. 2. Clean, professional, broadsheet-style publication. 3. No admin system. The site and its content take care of itself. I publish articles on a site that has an RSS feed, and I publish a podcast that has an RSS feed, so this site consumes both and the source of truth is where the content is originally published. 4. Plain English. Clear, precise, human. Read the About page or the Privacy Policy. I'm not trying to hide behind technobabble, only clarity. 5. No Cookies. No Tracking. No Analytics. No Recommendation Engine. No Profiling. No Selling or Sharing of Personal Data, clearly stated as a deliberate decision not an oversight seeking correction. Here are some example pages, I'd encourage you, if you so wish, to visit the site and let me know your thoughts: smarterarticles.fm (https://smarterarticles.fm)
0
64
Cover image for Continuing from yesterday, some further
Continuing from yesterday, some further concepts....
2
103
Ollama(2)
Abdullah Amir's avatar
Abdullah Amir
proIslamabad, Pakistan
Full-Stack & AI Developer | React Native, Next.js, AI Agents
5.0
Rating
3
Followers
Full-Stack & AI Developer | React Native, Next.js, AI Agents
Cover image for Not every OnSense user is
Not every OnSense user is on the mobile app — some just want to ask a quick question about their appliance from a browser. Appliance GPT was built as a standalone web product: a focused, consumer-facing chat interface where anyone can describe an issue or ask about error codes, parts, or repairs and get an answer trained on appliance-specific knowledge, without needing to install anything. What I built I built the chat UI solo, using React and Next.js — the conversational interface, message flow, and front-end experience that consumers interact with directly at appliancegpt.onsense.ai (http://appliancegpt.onsense.ai). Stack: Next.js and React for the web chat interface Integration with OnSense's underlying AI/repair-knowledge backend What shipped A live, standalone web app giving consumers direct access to an AI appliance-support assistant — no app download required, just open the browser and ask.
0
39
Cover image for SeaRebbel Marine Autopilot Navigation App
SeaRebbel Marine Autopilot Navigation App
0
0
Cover image for Unified Commerce Platform for Habbal Jewellery
Unified Commerce Platform for Habbal Jewellery
0
2
Cover image for Most people trying to fix
Most people trying to fix a home appliance are stuck flipping through a PDF manual or guessing which part is causing an issue. OnSense set out to replace that with an app where entering a model number instantly surfaces specs, part breakdowns, and an AI assistant trained specifically on appliance repair knowledge — not a generic chatbot. What I worked on As part of the mobile engineering work on the React Native (Expo) app, I built the OCR module that lets users scan an appliance's nameplate with their camera to automatically identify the model and pull it into the system — removing the need to manually type in model numbers that are often worn, tiny, or hard to read. Stack: React Native (Expo) for iOS and Android OCR/camera-based scanning for nameplate recognition AI chat integration (OnSense GPT) for appliance-specific Q&A Backend integration with the platform's parts and repair-knowledge database What's in the app: Model lookup by number, with detailed specs and part breakdowns Exploded View module — an interactive, clickable diagram of appliance parts OnSense GPT chat assistant for error codes, repair steps, and part compatibility Nameplate scanning via OCR for fast, accurate model identification Parts cross-referencing against verified compatibility databases
3
1
169
Ollama(1)
Anurag Nagare's avatar
Anurag Nagare
Mumbai, India
I’m an AI & Machine Learning engineer with expertise in deve
I’m an AI & Machine Learning engineer with expertise in deve
Cover image for It all started on a
It all started on a Sunday at the AWS User Group Mumbai meetup. I wasn't expecting to walk away with a new obsession, but then the speaker introduced me to Temporal and everything changed. Temporal is a durable execution engine that solves one of the hardest problems in agentic AI what happens when your LLM workflow crashes mid-run? Normally you lose everything So I went home and built this: an agent that monitors your competitors around the clock tracking pricing changes, product launches, hiring signals, and strategic moves. Every 24 hours it uses Mistral (running fully on-device via Ollama) to analyze the data and synthesize a structured executive briefing delivered straight to your inbox. Sometimes the best projects start with a Sunday conversation. https://github.com/AnuragNagare/Agentic-AI-.git
0
77
Cover image for One Gate: Voice-controlled Gmail, Calendar,
One Gate: Voice-controlled Gmail, Calendar, and Drive that can't fire the wrong thing Every "AI agent" demo shows a voice command turning into a sent email like magic, but almost nobody shows the part that actually matters: what stops it from sending the wrong thing. I built proof: an agent that runs your Gmail, Calendar, Contacts, and Drive by voice reply to a thread, schedule a meeting, archive an email, find a file hands-free end to end, but never fires anything irreversible without you saying so. The honest hard part isn't getting an LLM to sound smart, it's this: a transcript goes to LLM against a strict JSON schema and comes back as an ordered plan, every step tagged reversible or not and exactly one thing in the whole system is allowed to check that flag. Finding a thread, drafting a reply, creating a calendar event: those just run. The result covers real ground without ever feeling like it's guessing: forward or reply to email with the original quoted underneath, archive/label/trash, resolve a name to a real address through your Contacts first and your mail history as fallback, schedule an event that creates quietly and only emails the invite after a second confirmation, answer "what did John say" or "what's on my calendar Thursday" grounded in content actually fetched from your account not hallucinated. No backend, no server anywhere in the loop
0
28
Cover image for What every "AI gesture control"
What every "AI gesture control" demo quietly leaves out Everyone films a hand waving at a screen and calls it AI. Almost nobody shows what's underneath that there's usually no gesture model at all. A "grab" is one distance crossing a line. Here's proof. I built a jigsaw puzzle you solve with your bare hands no mouse, no controller, no gesture classifier, no training.
0
58
Cover image for Everyone's building AR filters and
Everyone's building AR filters and calling it "computer vision magic." Almost nobody's asking what's actually happening underneath — that most of these effects are just clever masking, not detection. Here's proof. I built an invisibility cloak that runs entirely in the browser, no green screen, no chroma key, no model training. https://github.com/AnuragNagare/Ghost-frame
4
2
273
Ollama(1)