Projects looking for builders.

TuneAfrica — Pan-African Music Streaming Platform

TuneAfrica is a music streaming platform purpose-built for African artists and listeners, addressing the fundamental limitations of global platforms like Spotify and Apple Music in the African context. Global platforms pay African artists at global per-stream rates that effectively undervalue African music relative to local purchasing power; they catalogue African music poorly, grouping diverse genres under blunt tags like "Afrobeats" that erase the distinctions between Amapiano, Afrohouse, Bongo Flava, Afrofusion, and dozens of other genres; and they optimise discovery for Western listening patterns rather than the social, communal music consumption patterns common in African contexts. TuneAfrica is built for Africa first. The artist monetisation model is calibrated to local purchasing power parity — a stream in Kenya generates revenue calculated against Kenyan consumer prices, not US prices. The genre taxonomy is built from the ground up by African music journalists and cultural experts, with hundreds of granular genre and subgenre tags. The social listening and discovery features are designed around the African social music experience: group listening sessions, viral challenge mechanics tied to popular dance genres, and community playlist curation. The technical architecture must solve the bandwidth problem. With a significant portion of our users on 2G and 3G connections and limited data budgets, audio streaming quality must adapt aggressively to available bandwidth, downloads for offline listening must be efficient and well-managed, and the UI must be fast and lightweight. We use HLS adaptive bitrate streaming for online listening and Opus-encoded files for offline downloads, with an intelligent prefetch system that downloads the next few songs in a playlist when on WiFi. The platform includes: a B2C music streaming app for listeners; a self-service distribution portal for independent artists to upload music, set royalty splits for collaborations, view streaming analytics, and receive payments via M-Pesa; a label management portal for record labels managing multiple artists; and a licensing portal for brands, film producers, and content creators seeking sync licences for African music. The recommendation engine is a core differentiator — it uses collaborative filtering, content-based analysis of audio features (BPM, key, energy, danceability), and cultural context signals (region, language, genre heritage) to surface music that listeners will love but would never find on global platforms.

10 months·3 milestones·5 roles

AfriVote — Digital Civic Participation Platform

AfriVote is a digital civic participation platform that enables African governments, county administrations, and civil society organisations to conduct transparent public consultations, community referenda, and participatory budgeting exercises. The platform addresses a critical deficit in African governance: despite vibrant civil societies and constitutionally mandated public participation requirements, most engagement between governments and citizens happens in poorly-attended physical barazas that exclude women, youth, and rural populations. AfriVote provides a secure, auditable digital channel for civic voice. Citizens can verify their identity using their national ID, submit structured or free-text opinions on proposed policies and budgets, vote in community referenda, and track the government's response to their submissions. Government officials can launch consultations, analyse public sentiment in real time, publish response commitments, and generate audit trails that demonstrate constitutional compliance. The security and integrity of the platform is paramount. Every vote and submission is cryptographically signed with the citizen's key derived from their verified national ID. A Merkle tree audit trail ensures that no submission can be altered or deleted without detection. Zero-knowledge proofs allow citizens to prove they participated without revealing how they voted in secret ballot consultations. The system is designed to be resistant to both state-level censorship (through decentralised architecture options) and to organised fraud (through rate limiting, duplicate detection, and biometric verification tiers). The platform supports multiple modalities of engagement: structured surveys and questionnaires for policy consultations; ranked-choice voting for community decisions; participatory budgeting where communities allocate simulated budget amounts across competing priorities; and free-text submissions with AI-powered sentiment analysis and thematic clustering that helps officials understand public opinion at scale. Mobile accessibility is designed for Kenya's USSD fallback requirement — citizens without smartphones can participate via SMS and USSD codes. The web and mobile app provide richer engagement for users with better connectivity. SMS voting uses a cryptographic challenge-response protocol to prevent ballot stuffing.

10 months·3 milestones·4 roles

LogiTrack — Real-Time Fleet & Logistics Platform

LogiTrack is a comprehensive fleet management and logistics orchestration platform designed for East Africa's growing e-commerce and logistics sector. The platform serves freight companies managing long-haul truck fleets, courier companies managing last-mile motorcycle and vehicle fleets, and enterprise clients who need supply chain visibility across multiple third-party logistics providers. The East African logistics market has specific characteristics that make standard Western fleet management solutions a poor fit: roads are in varying condition and GPS accuracy in dense urban areas like central Nairobi is poor; fuel theft and route deviation are significant operational problems; drivers may be semi-literate and need a simple, SMS-fallback-capable interface; and cargo theft on high-crime routes requires active monitoring and rapid response capabilities. LogiTrack addresses these needs with a real-time GPS tracking engine that processes location pings from IoT GPS trackers on vehicles every thirty seconds, filtering out GPS noise and reconstructing probable routes when signal is lost. The route optimisation engine calculates optimal routes considering current road conditions (sourced from Google Maps and our own crowdsourced data layer), known congestion patterns, and customer delivery windows. The driver app provides turn-by-turn navigation, proof-of-delivery capture, and issue reporting in a single lightweight interface. The platform includes: an advanced geofencing engine with polygon zones for loading bays, restricted areas, and customer sites; a fuel monitoring integration that correlates GPS mileage with fuelling events to detect fuel theft; an automated maintenance scheduling system based on mileage and engine-hours from OBD-II data; a cargo temperature monitoring integration for pharmaceutical and perishable freight; and a customer self-service portal with live shipment tracking and electronic proof of delivery. The architecture is event-driven: a high-throughput message broker (Kafka) receives all GPS and IoT events, real-time processing (Apache Flink) computes vehicle state and triggers alerts, and persistent storage uses TimescaleDB for time-series location data and PostgreSQL for transactional data.

12 months·4 milestones·5 roles

EduBridge — Adaptive Learning Management System

EduBridge is an adaptive learning management system designed for African universities and vocational training institutions, addressing a fundamental problem in African higher education: the gap between what institutions teach and what the labour market needs. Traditional African university curricula are often five to seven years behind industry requirements, content is delivered in a one-size-fits-all format that does not accommodate different learning styles, and students receive almost no personalised feedback on their progress. EduBridge addresses this through three core innovations. First, an industry-aligned curriculum mapping engine that connects each course module to specific industry competencies and current job market demand data, so that both students and institutions can see the relevance of what is being taught. Second, an adaptive learning path algorithm that adjusts the sequence, depth, and format of content based on each student's demonstrated knowledge, learning velocity, and career goal. Third, an automated assessment engine that generates novel questions from learning objectives, reducing plagiarism while providing rich diagnostic feedback. The platform is designed for the African higher education context: it must work on low-bandwidth connections, support USSD fallback for key functionality where smartphone access is limited, integrate with Pesapal for fee collection, and support the administrative workflows of African universities including letter-grade transcripts, semester-based timetabling, and examination board reporting formats. The content authoring environment is built for African educators who may not be technically sophisticated — a Notion-like block editor that supports text, video (with automatic compression and CDN delivery), interactive exercises, code sandboxes for programming courses, and quiz builders. Content is AI-assisted: the system can auto-generate quiz questions, suggest related resources, and flag content that conflicts with recent industry updates. The technical stack is Next.js for the frontend, Node.js/NestJS for the backend, PostgreSQL for structured data, MongoDB for learning content documents, Redis for real-time features, and AWS S3 with CloudFront for media delivery.

8 months·3 milestones·3 roles

FarmConnect — Agritech Marketplace & Advisory

FarmConnect is an integrated agritech platform that addresses three interconnected problems facing smallholder farmers in East Africa: access to markets, access to inputs, and access to agronomic expertise. Smallholder farmers — who produce seventy percent of Kenya's food — typically sell their produce through middlemen at prices far below retail, buy inputs at inflated prices from local agroshops without quality assurance, and receive agronomic advice that is generic, infrequent, and often wrong. FarmConnect solves these problems through three linked products. The marketplace connects farmers directly to institutional buyers — supermarkets, processors, export agents — enabling price discovery and transparent contract farming arrangements. The input marketplace allows certified agrodealers to list seeds, fertilisers, and crop protection products with verified quality certifications, and allows farmer cooperatives to aggregate orders for bulk pricing. The AI advisory engine provides personalised, localised advice based on the farmer's specific crop, soil type, location, rainfall pattern, and current market prices. The AI advisory engine is the most technically interesting component. We are building a fine-tuned LLM that has been trained on Kenya's agricultural extension service knowledge base, County agricultural officer reports, CIMMYT crop research publications, and aggregated farmer outcomes from our platform. The model will provide advice in Swahili and Kikuyu as well as English, and will be accessible via WhatsApp as well as the mobile app — critical for farmers who are comfortable with WhatsApp but have not yet adopted dedicated apps. The marketplace logistics layer integrates with motorcycle courier networks for last-mile delivery of inputs and a network of aggregation points for produce collection. The platform also includes a financial layer: farmers can access input financing through a partner SACCO, with repayment automatically deducted from their produce sale proceeds. The stack is Python/FastAPI for the backend, React Native for the mobile app, PostgreSQL for transactional data, and a vector database for the AI advisory knowledge base.

6 months·3 milestones·3 roles

AfriHealth — Rural Telemedicine Platform

AfriHealth is a telemedicine platform purpose-built for rural and peri-urban communities in East Africa, where the nearest clinic may be an hour away and the nearest specialist several hours further. The platform connects patients with doctors and nurses via video consultation, enables digital prescription and pharmacy delivery, and provides community health workers with digital tools to conduct assessments, track patient outcomes, and escalate cases requiring specialist attention. The platform addresses a critical gap in healthcare access. According to Kenya's Ministry of Health, there are fewer than two doctors per ten thousand people in rural counties. Telemedicine does not replace in-person care, but it dramatically extends the reach of the health system — allowing a patient in Turkana to consult a cardiologist in Nairobi without a fourteen-hour journey. The technical architecture centres on a progressive web app that works on low-end Android devices with intermittent 3G connectivity. The video consultation engine will be built on WebRTC with a TURN server fallback for NAT traversal in challenging network environments. We will implement adaptive bitrate video that degrades gracefully to audio-only when bandwidth is insufficient. The appointment booking and queue management system must work reliably offline, syncing when connectivity is restored. The patient health record is the most sensitive component — we are implementing FHIR-compliant data structures, end-to-end encryption for all health data at rest and in transit, and role-based access control that ensures a community health worker can only see the patients they are responsible for. We are integrating with Kenya's National Health Insurance Fund (NHIF) for coverage verification and claims submission. The backend is Python with FastAPI and PostgreSQL, chosen for the rich ecosystem of healthcare and NLP libraries available in Python, particularly for medical entity extraction from clinical notes. The frontend is a Next.js PWA deployed as both a web app and a lightweight Android wrapper via Capacitor.

7 months·3 milestones·3 roles

Savannah Pay — Pan-African Mobile Wallet

Savannah Pay is an ambitious pan-African mobile wallet platform designed to serve the forty percent of Sub-Saharan Africans who remain unbanked or underbanked. The project vision is to build a single application that works seamlessly across Kenya, Uganda, Tanzania, Ghana, and Nigeria — handling local currency accounts, cross-border transfers at transparent rates, mobile money integrations in each market, and a merchant payment layer that allows small businesses to accept digital payments without expensive POS hardware. The technical challenge at the heart of Savannah Pay is building a multi-currency, multi-rails payment architecture that abstracts over the very different mobile money ecosystems in each country. In Kenya we integrate with Safaricom M-Pesa via Daraja API. In Ghana we work with MTN Mobile Money and Vodafone Cash. In Nigeria we integrate with Flutterwave and Paystack as intermediaries for bank transfers. The system must handle currency conversion, reconciliation, and compliance reporting across five regulatory regimes simultaneously. The mobile application will be built in Flutter for maximum code reuse across Android and iOS, with a strong emphasis on performance on low-end devices and offline resilience. The backend will be a microservices architecture in Node.js, with separate services for accounts, transactions, notifications, KYC, and compliance. All services will be containerised and deployed on Kubernetes, with event-driven communication through Kafka for transaction events and webhook delivery. KYC and identity verification is a particularly complex component — each market has different national ID types, different acceptable selfie and document quality thresholds, and different regulatory requirements for tiered KYC. We are integrating with Smile Identity for document verification and liveness detection, with a custom workflow engine that routes verification requests to the appropriate market-specific process. The project will be built in three phases: Phase 1 covers Kenya and Uganda with M-Pesa and MTN integrations; Phase 2 adds Ghana and Nigeria; Phase 3 adds merchant QR payments and the cross-border transfer product. We are seeking a core team of four specialists to build alongside Fatima as project lead.

9 months·3 milestones·4 roles

B2B E-commerce Web Platform

Overview: Building a B2B e-commerce platform for a wholesaler in Dar es Salaam to manage orders from small retailers across the city. The platform will include inventory management, merchant accounts, and integrated mobile money checkout. This project is part of a larger digital transformation to streamline the distribution of consumer goods. Deliverables: - A high-quality React web application for retailers to browse and order goods. - An admin dashboard for the wholesaler to manage inventory and fulfillment. - Integration with local payment gateways (M-Pesa, Tigo Pesa). - Secure user authentication and account management. Tech Stack: - React, Next.js, Node.js, PostgreSQL, M-Pesa API. Team Structure: - 1 Senior Full-Stack Engineer, 1 Junior Developer.

4 months·2 milestones·2 roles

Alternative Credit Scoring ML Model

Overview: Developing a machine learning model to predict creditworthiness for informal sector workers who lack traditional credit histories. We will use alternative data sources like mobile money usage, airtime purchases, and utility bill payments to generate scores. This project aims to expand financial inclusion for thousands of unbanked individuals. Deliverables: - A trained ML model with documented performance metrics (AUC, Precision/Recall). - Data ingestion and feature engineering pipelines for alternative data. - An API endpoint for real-time credit score retrieval. - A technical report on feature importance and model interpretability. Tech Stack: - Python, Scikit-learn, XGBoost, Pandas, SQL. Team Structure: - 1 Lead Data Scientist, 1 Data Engineer.

5 months·2 milestones·2 roles

lock2 of 2 funded

Telemedicine Consultation Platform

Overview: Developing a secure web-based telemedicine platform for a network of clinics in Kampala. The platform will facilitate video consultations, electronic health records (EHR) management, and integrated billing through mobile money. This project aims to improve access to specialist care for urban and semi-urban populations. Deliverables: - A secure React frontend for both doctors and patients. - Backend API for managing patient data and appointment scheduling. - Video conferencing integration using WebRTC or a 3rd party provider (e.g., Twilio). - Integrated payment module for M-Pesa and Airtel Money payments. - Compliance with Ugandan health data regulations. Tech Stack: - React, Node.js, MongoDB, WebRTC, M-Pesa API. Team Structure: - 1 Lead Full-Stack Engineer, 1 UI/UX Designer, 1 Backend Specialist.

6 months·3 milestones·2 roles

lock3 of 3 funded

M-Pesa Payment Gateway Integration

Overview: We are digitizing the payment flows for a large regional SACCO in Central Kenya. This project involves integrating our core platform with the M-Pesa C2B and B2C APIs to allow members to deposit and withdraw funds directly from their mobile wallets. This is a critical step in our mission to bring modern financial services to community-based organizations. Deliverables: - A robust Node.js middleware for handling M-Pesa Daraja API calls. - Secure webhook endpoints for real-time transaction confirmation. - A merchant-facing dashboard for tracking transaction status and reconciliations. - Detailed technical documentation and unit test coverage. - Deployment to an AWS-based staging environment. Tech Stack: - Node.js (TypeScript), Express.js, PostgreSQL, Redis, M-Pesa Daraja API. Team Structure: - 1 Lead Backend Engineer (Project Lead), 1 Junior Developer, 1 QA Specialist. - The client team will provide access to the sandbox and production credentials.

3 months·3 milestones·2 roles

lock3 of 3 funded