Solana-Native Runtime • Near AGI Agent Intelligence

Near AGI for Solana

Solana Agent combines strong reasoning, persistent memory, and native onchain execution in one hosted runtime. Built for teams that need agents that can plan, act, and keep context across real Solana work.

Near AGI planning, debugging, and follow-through
Native Solana actions for research, swaps, and DeFi tasks
Agent-paid x402 settlement on Solana in USDC or USDT
Persistent memory across sessions and projects
Dollar-equivalent pricing with clear retention choices

Runtime

One runtime for the hosted service.

Solana Agent connects wallets, tools, orchestration, and hosted chat and memory access.

Start Building Pricing

Hosted

Hosted inference for production traffic.

Hosted inference where the agent pays via x402 on Solana in USDC or USDT, with dollar-equivalent pricing across chat and memory products. Works with a private key or Privy embedded signing for secure wallet access.

See Pricing Docs

Near AGI Intelligence, Native to Solana

Solana Agent pairs strong reasoning with native Solana execution, persistent memory, and hosted delivery. It is built for agents that need to think well, act reliably, and keep context in production.

Near AGI Reasoning

Plans, adapts, debugs, and completes multi-step work with the kind of follow-through teams expect from a strong operator, not a stateless chatbot.

Native Solana Execution

Built-in tools for swaps, research, wallet actions, and DeFi workflows keep the model close to the chain instead of routing through brittle glue code.

Persistent Memory

Carries goals, prior decisions, and project context across sessions so long-running workflows stay coherent instead of resetting every turn.

Reliable Tool Orchestration

Coordinates multiple tools and steps without losing the objective, making it practical for research, trading, support, and internal automation.

Production Recovery

Handles failures, retries safely, and resumes work with context instead of collapsing after a single bad tool call.

Hosted for Real Traffic

Usage-based products, clear retention choices, and explicit priority behavior make it easier to ship customer-facing agents on Solana.

Near AGI Intelligence for Solana

A hosted runtime that can reason through multi-step work, make grounded decisions, and execute natively on Solana without losing the thread.

Plans and executes complex tasks
Connects reasoning directly to actions and flows
Built for production agents, not demo chat

GitHub Read Overview

Persistent Memory & Onchain Action

Keep context across sessions while using native Solana tools for swaps, research, and DeFi execution. The agent remembers the job and can continue it.

Coherent recall across longer customer workflows
First-party tools for wallet, market, and DeFi
Recovery paths that help work continue after failures

GitHub API Docs

Hosted Delivery for Real Customers

Customer-facing delivery with clear pricing, retention options, streaming responses, and priority handling for the workloads that need it.

Standard and priority products
Streaming and idempotency support
Retention options matched to short and long-running work

See Pricing API Docs

How Pricing Works

Pick the hosted product first. Eligible chat and 7-day memory traffic start each calendar month on Explorer starter pricing, then roll into standard or priority product rates as usage grows.

Product

Hosted Chat

Stateless traffic and one-off requests. Explorer-eligible each calendar month.

Input: $5 / 1M tokens
Output: $30 / 1M tokens
Retention: None
Explorer: Yes, automatic when eligible

Product

Hosted Memory

Persistent agents and workflows with 7-day work retention. Explorer includes this memory tier.

Input: $10 / 1M tokens
Output: $60 / 1M tokens
Retention: 7 days included
Explorer: Yes, 7-day memory included

Product

Hosted Memory

Persistent agents and workflows with 30-day project retention.

Input: $10 / 1M tokens
Output: $60 / 1M tokens
Retention: +$0.50 / request for 30 days
Explorer: No, standard token pricing

Explorer stage

Starter pricing without a separate plan

Explorer is additive. Eligible Hosted Chat and Hosted Memory with 7-day work retention start on lower token rates each calendar month, and then fall through to the normal product pricing once that allowance is used.

Volume discounts apply only to token-priced usage after Explorer is exhausted. The 30-day project-memory surcharge stays unchanged.

Explorer input

$1.50 / 1M

Applied before standard input pricing on eligible monthly usage.

Explorer output

$9 / 1M

Applied before standard output pricing on eligible monthly usage.

Allowance

200k in / 40k out

Resets every calendar month per wallet account.

Memory included

7-day work tier

Project retention still uses standard token pricing and adds $0.50 / request.

Service tier

Standard service

Base rate

Default tier for chat and memory. Requests queue under load and bill at the standard product rate.

Service tier

Priority service

2x only when delivered

Available on chat and memory. If unavailable, the request falls back to standard billing and standard handling.

Volume discounts

Automatic monthly token discounts

Once Explorer allowance is exhausted, monthly token usage can reduce standard or priority token pricing automatically. Project-memory request fees do not receive these discounts.

5M monthly tokens

15% off

Applies to token-priced usage after Explorer allowance is consumed.

20M monthly tokens

25% off

Higher monthly throughput automatically moves the wallet into the next discount tier.

100M monthly tokens

35% off

The deepest tier applies only to token charges, not the 30-day project-memory surcharge.

Products

Compare the hosted products directly: chat, memory with 7-day retention, and memory with 30-day retention, each available at standard or priority service.

Decision point	Hosted Chat Standard	Hosted Chat Priority	Hosted Memory 7 days / standard	Hosted Memory 7 days / priority	Hosted Memory 30 days / standard	Hosted Memory 30 days / priority
Best for	One-off requests	Latency-sensitive traffic	Persistent agents	Urgent persistent agents	Longer-running projects	Urgent longer-running projects
Input price	$5 / 1M	$10 / 1M*	$10 / 1M	$20 / 1M*	$10 / 1M	$20 / 1M*
Output price	$30 / 1M	$60 / 1M*	$60 / 1M	$120 / 1M*	$60 / 1M	$120 / 1M*
Explorer stage	First 200k in / 40k out monthly	Same allowance before priority billing	First 200k in / 40k out monthly	Same allowance before priority billing	Not eligible	Not eligible
Service tier	Standard	Priority	Standard	Priority	Standard	Priority
Memory retention	None	None	7 days	7 days	30 days	30 days
Extra memory fee	None	None	None	None	+$0.50 / request	+$0.50 / request
Queue treatment	Standard queue	Priority queue when available	Standard queue	Priority queue when available	Standard queue	Priority queue when available

* Explorer stage pricing applies to Hosted Chat and Hosted Memory with 7-day work retention at $1.50 / 1M input and $9 / 1M output for the first 200k input and 40k output tokens each calendar month. Priority pricing is 2x only when priority is actually delivered. If priority is unavailable, billing falls back to the standard product for that same request. Hosted Memory with 30-day project retention adds $0.50 per request and stays on standard token pricing. Volume discounts apply only to token-priced usage, not the project-memory surcharge: 15% off at 5M monthly tokens, 25% off at 20M, and 35% off at 100M.

Security & Transparency

This site never asks for seed phrases. Hosted usage is billed per request, with clear retention and priority rules so customer-facing behavior stays predictable.

Links