Hackathon #3
Agentic Apps, PoI/PoUW & Developer Tools
Following the momentum of Hackathon #2, we’re launching Hackathon #3 to push deeper into agentic applications, public goods, and developer tooling on decentralized inference.
Hackathon Format (unchanged): Open‑ended runs continue — variable inflow = high‑value edge‑case data. We’ll keep inviting outsiders to try agentic apps while hardening software, docs, and process.
Objective
Build proof‑of‑concept (PoC) applications, bots, validators, or developer tools that leverage Cortensor’s decentralized inference protocol.
Primary focus areas:
Agentic Applications — autonomous/semi‑autonomous assistants that act, monitor, transact.
PoI/PoUW Utilization — leverage redundant inference (PoI) and validator scoring (PoUW) where it adds trust; show how your app uses or exposes these features.
Validation & Attestations (PoI/PoUW) — use validator features to score results, produce evidence bundles, and optionally write on‑chain records.
App Stores & Catalogs — discovery surfaces for Cortensor apps with one‑click public demos.
Developer Tooling & SDKs — packages, CLIs, wrappers, and templates for smooth integration.
Public Goods / Free Inferencing — open bots and apps for the community.
Infra Observability — dashboards for inputs/throughput/latency, miner reputation, model usage.
Stretch goals (bonus points): Note: COR Prover, ERC‑8004, and x402 are internal R&D and optional — not required for Hackathon #3.
ERC‑8004: emit agent identity/validation artifacts for discoverability.
x402: pay‑per‑call rails or UI flows for usage‑based access.
Router Surfaces: integrate Router v1 (REST) with a /validate endpoint; prototype COR Prover surfaces; explore MCP.
Prize Pool (in $COR equivalent)
1st: $1000
2nd: $800
3rd: $500
4th–5th: $300 each
6th–7th: $150 each
8th–10th: $100 each
11th–20th: $50 each
Ongoing Support: Top projects may qualify for monthly $COR grants for continued maintenance and improvements.
Important Notice on Prize Payouts (eligibility condition)
To align incentives with Cortensor’s long‑term growth: if a prize‑winning participant is not (a) an existing node operator running >20 nodes, or (b) a holder of $500+ $COR prior to kick‑off, or (c) a participant with active staked tokens, then their prize will be split:
50% allocated directly to Staking Pool #1 under their address
50% distributed upfront as liquid $COR
This ensures rewards both support winners and strengthen network security and staking participation.
Judging & Awarding Policy
Quality over rank: Prizes are not awarded strictly by leaderboard order. Cortensor will judge qualified entries on overall quality, impact, technical rigor, usability, documentation, and alignment with Cortensor’s roadmap.
Discretionary placement: Judges may award a prize to any qualified entry at a given place (e.g., a lower-ranked but higher-quality project may receive a higher prize tier).
No guarantee to fill all places: Cortensor may withhold or reallocate any prize tier if submissions do not meet the quality bar.
Ties / partial awards: Cortensor may declare ties, split awards, or issue honorable-mention grants at its discretion.
Compliance: Entries must comply with all rules; violation may result in disqualification and forfeiture of prizes.
Suggested Project Ideas
New and Emphasized for #3
Agentic Assistants (Expanded):
Research Ops Agent — reads repos/docs, tracks issues, posts weekly summaries.
DevOps Agent — monitors routers/validators; triggers alerts or creates tickets.
On‑Chain Agent — interacts with smart contracts; validates data/receipts; posts attestations.
Workflow Coordinator — orchestrates tools/APIs with Cortensor as the inference layer.
PoI/PoUW Validation Utilities (no COR Prover requirement):
Implement rubric‑driven scoring, embedding distance checks, deterministic policy tests.
Optionally output validation artifacts/evidence bundles (e.g., JSON + IPFS).
If helpful, expose a simple validation endpoint; demonstrate redundancy or cross‑model checks.
App Stores & Catalogs 2.0:
Search/tags/filters; popularity leaderboards; “Try it now” demos.
Tooling/SDKs & CLIs:
Python/JS/TS/Rust SDKs for session management & task routing.
CLI for deploy/test/monitor; templates for bots/agents/oracles.
Memory & Knowledge Layers:
Memory‑as‑a‑service for agents; decentralized knowledge bases with inference‑backed QA.
Observability/Analytics:
Miner reputation, latency heatmaps, model usage analytics, validator dashboards.
Still Great from #1/#2
AI Oracle (Truth‑as‑a‑Service) via multi‑node consensus
Cortensor Community Bot with decentralized inference backend
Basic AI Agent (Function‑Calling) — bookmarking, summarization, etc.
Price & Sentiment Bots — multi‑site scraping + LLM sentiment + proofs
Ongoing Support
Outstanding projects may receive monthly $COR grants for ongoing improvements.
Exceptional teams may be offered dedicated roles in the Cortensor developer community.
How to Participate
Join Discord: discord.gg/cortensor
Build openly in the community repo: github.com/cortensor/community-projects
Submit your final app with a clear README showing functionality and Cortensor integration.
Deliverables Checklist:
Public repo with permissive license (e.g., MIT/Apache‑2.0)
README with quickstart + runbook + architecture diagram
Demo link (live URL or recorded video) + instructions to reproduce
For validators: rubric prompt(s), embedding spec, deterministic checks
For agents: action list, tool integrations, safety guardrails
Timeline
Kick‑off: Mon, Nov 21, 2025
Submission deadline: Sun, Jan 4, 2026
Duration: ≈6 weeks. If dates shift, we’ll announce updates in Discord.
Evaluation Criteria
Mandatory: Working public demonstration during the hackathon (Discord/Telegram or designated channel). Projects not demonstrated will not qualify.
Scoring rubric:
Functionality & Stability — 25%
Integration with Cortensor (sessions, routing, validators, staking/payment flows; PoI/PoUW where applicable) — 25%
Originality & Technical Depth — 20%
Usability & Demo Quality — 20%
Public Good Impact (free access, docs, community value) — 10%
Bonus Considerations: ERC‑8004 artifacts, x402 flows, COR Prover /validate usage, on‑chain records, tests/benchmarks, observability dashboards.
Cortensor’s Discretion: Cortensor reserves the right to evaluate, rank, and award prizes based on the above and other relevant factors.
No Auto‑Generated Submissions: Purely AI‑generated entries without working implementation do not qualify.
Terms & Notes
Internal Works (FYI): COR Prover, ERC‑8004, and x402 are internal/WIP and not required for Hackathon #3. Focus on currently available PoI/PoUW features.
Safety/Compliance: Projects must follow applicable laws and reasonable safety guidelines.
Transparency: Clearly mark any centralized components or paid services used.
Data: Use public or properly licensed datasets/APIs.
Contact: Questions and office hours will be posted in Discord.
Hackathon #3 continues our push into the agentic frontier — building applications that don’t just infer, but act, coordinate, validate, and serve the community.
Let’s build the next wave of decentralized AI together.
Last updated