Every answer is economically verifiable on-chain — a cheating miner is slashed, automatically. Private inference on consumer GPUs, paid in a fixed-supply token. A sovereign Cosmos SDK L1.
Proof-of-Work burns gigawatts on meaningless hashes. Dendra secures a market for what people actually want from GPUs today: AI inference — done privately, verified statistically, and paid for under an honest-stake majority.
Miners are GPU owners running a real LLM. The work the chain rewards is verified inference for paying clients — not hashing. A consumer GPU is enough to take part.
Prompts are end-to-end encrypted client↔miner (X25519 + AES-256-GCM). The relay and the chain only ever see hashes, embeddings and metadata — never your content.
Most jobs settle instantly. A random sample is re-checked by a fresh, VRF-selected committee that judges the answer with an LLM — and a wrong answer is slashed hard. Cheating is made loss-making, not merely discouraged.
Any OpenAI-compatible client points at the Dendra gateway and uses the network without even knowing it. The chain never sees your content.
The client encrypts the prompt to the miner's key and sends it via the OpenAI-compatible gateway. The chain sees only a fee and a job id.
The fee is escrowed in a module account. An unpredictable on-chain VRF beacon (anti-grinding) assigns the job — the requester can't pick its friends.
The assigned miner runs the model on its GPU and is paid optimistically. Plaintext exists only in RAM during compute, behind sealed-memory and egress guards.
A random share of jobs is re-checked by a fresh, VRF-selected committee that judges the answer with an LLM. A wrong — or silent — miner is slashed hard.
A slash is invisible inside a normal chat — so we put it on the table. The explorer below reads the chain and lists audited jobs and real slashes, live. It's the one thing no closed model can show you.
Every record here is a real, replayable on-chain event, read live from the network — audited jobs and the slashes that back every answer.
Every record here is independently replayable: pull the chain, re-run the audit, get the same verdict.
End-to-end encrypted client↔miner (X25519 ECDH + AES-256-GCM) — nothing in clear at the relay or on-chain. On consumer GPUs the miner decrypts in RAM to compute, guarded by sealed memory, egress and disk guards, software attestation and slashing.
On datacenter GPUs (NVIDIA Hopper / Blackwell), inference can run inside a hardware secure enclave for cryptographic confidentiality — an opt-in tier for regulated workloads.
$DNDR is what you pay for inference and what miners earn. A hard 10M cap, with every reward released from a pre-allocated Reserve — never minted into existence.
Base unit udndr · 1 DNDR = 1,000,000 udndr. A 4,000-run Monte-Carlo of the model keeps supply ≤ 10M in 100% of runs.
A real network with the full inference economy on-chain — every layer below is live and open source.
On-chain escrow, VRF assignment, optimistic verification with an LLM judge, replay-safe settlement, real-coin emission, bonds, slashing and burn — with hard slashing proven live on-chain, zero honest miners penalized.
Illegal-content filtering at the gateway, a replayable on-chain slash activation that powers “The Proof”, a public incentivized testnet, an OpenAI-compatible chat app, and monetization with buy & burn on real revenue.
One-click miners for community GPU owners, throughput measured on a real multi-validator network, and a broad, cross-hardware operator set.
A hardware-isolated privacy tier and verifiable, slashable inference for demanding use cases. Image generation is on the roadmap, behind a verification design built to the same standard.
The full network, secured by everything above.
Dendra is open source. Spin up a node on a consumer GPU, send a real prompt through the network, and watch it settle on-chain. You're paid from real job fees — honest work is rewarded, lazy or wrong work is slashed.