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
🚀 Level-3 Autonomous SRE Agent powered by CockroachDB Distributed Vector Search & AWS Bedrock Claude 3.5 Sonnet with Managed MCP Human-in-the-Loop Voice Governance 🛡️
Multi-tenant agent memory where the isolation boundary lives in CockroachDB row-level security, not application code. Broken on purpose, repaired, and proven with a hash-chained receipt
Edge gateway for LLM agents: blocks injection, jailbreak, tool abuse. Rate limits + SHA-256 audit chain via Cloudflare Workers, D1, Pages. DEF CON 34.
An autonomous AI assistant that uses persistent agentic memory to track user preferences, inventory updates, and order history for seamless online shopping.
Your AI agents forget why. Chronicle remembers.
Turn scattered rescue and community needs into remembered, approval-gated action.
always-on memory for AI agents. semantic recall over a CockroachDB distributed vector index, and it survives a wipe. built on AWS Bedrock, Lambda and S3.
Autonomous AI compliance engine that matches regulatory circulars to enterprise contracts using CockroachDB vector memory & Gemini to prevent legal risk.
Your AI tools keep forgetting each other. OneMemory gives every MCP agent one shared, permanent memory in CockroachDB.
An AI-powered decision ledger that preserves objectives, evidence and actions, retrieves similar past decisions, and reveals what changed before the next decision is made.
FlowGrid Memory Runtime helps AI agents inherit trusted project decisions, tracking what is confirmed, pending, rejected, or superseded with evidence-backed updates.
The zero-trust firewall that stops AI agents from acting on poisoned memory.
An AI Powered Zero Trust IAM agent that remembers past access descisions to provide smarter, consistent, and explainable cloud access recommendations
An open-weight coding harness where CockroachDB is the agent's persistent memory. It reads real state, schema, and context from CockroachDB before it writes—so a cheaper model ships production code.
Agent memory on CockroachDB that provably changes actions
Autonomous Anti-Fraud Transaction Engine
An agent that remembers which research-pipeline repairs actually worked—and learns only from human-confirmed outcomes.
Persistent agentic memory via CockroachDB — MCP server with x402 payments for AI agents to store, search, and retrieve knowledge
Agentic forensic memory for deepfake detection: every analysis stored as a vector on CockroachDB, recalled by similarity, and queryable in natural language through an MCP agent.
An autonomous AI security agent powered by agentic memory that tracks enterprise access boundaries and dynamically catches broken access control flaws before they are exploited.
We gave an AI agent 517,401 real Enron emails, hid who was convicted, and it independently flagged the ringleaders. Every finding with an audit-trailed in CockroachDB memory.
Al that remembers forever, at global scale.
A CockroachDB-backed shared memory layer where concurrent agent writes are detected and resolved, never silently lost.
Yare gives AI agents a clean handoff: what changed, what’s true, and what needs review.
409 – 432 of 444
