Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
Sakhi: Breaking the tech barrier for 300M+ rural women with a voice-first AI companion, powered by Paritok 4B compression to cut token costs by 74% at scale.
An AI engineering assistant that understands repositories, visualizes architecture, and reduces LLM token usage with Paritok.
LensOpsAI is a Paritok-powered developer tool that compares full and compressed LLM context, measures real token savings, and detects when compression harms answer quality before deployment.
Rare neuroimaging cases hide in decades of unsearched literature. NeuLitTrace finds them, cites the source, on 88.3% fewer tokens, powered by Paritok.
PariPari is a repo-aware AI copilot that uses Paritok context compression to explore massive codebases, fix bugs, and generate PRs without blowing up LLM token limits or budgets.
Auditable Paritok compression for incident agents: remove repetitive logs, preserve exact IDs and errors, and prove the result before analysis.
The institutional memory that senior engineers carry in their heads — captured as semantic memory, retrieved by Ruby reflection, compressed by Paritok.
A working memory loop, not a longer prompt: MIRA carries decisions and corrections across sessions, retires what's outdated, and shows what shaped each answer.
Maximize your AI agent's efficiency and slash LLM API costs by 74% with intelligent context compression.
Evidence-safe warehouse change reviews with 67.6% less reasoning context.
An AI study companion where students upload their notes, ask questions, and use Paritok to compress document context reducing prompt tokens, API costs, and latency.
Save tokens. Compress prompts. Keep every detail.
Validate your outputs, Save your tokens!
Audits Paritok token savings against evidence retention in real LLM workflows.
The last time you'll pay full price to debug the same error twice.
nutsheLLM trims bloated LLM context with PariTok, protects exact facts, and validates task quality—backing off automatically when compression goes too far.
Two GitHub issues with reproducers and drop-in patches for the code paths that decide Paritok's dashboard numbers and startup UX.
a Plugin that makes AI agents faster and more productive: route skills, run workflows, shrink context (maping/and reducing), install across AI CLIs
An AI-powered digital twin that provides personalized learning paths, skill gap analysis, course recommendations, and career guidance for students.
25 – 43 of 43
