Agent Frameworks
Which frameworks and ecosystems a best for producing effective Internet Native Citizens?
| Name | GitHub | Language | Specialty/Agents | Token | DePIN |
|---|---|---|---|---|---|
| Archon | TRUE | Python | Agent for Building Agents | FALSE | FALSE |
| ai16Z Eliza | TRUE | TypeScript | Eliza, SpartenDegen | TRUE | TRUE |
| Almanak | NO CODE PLATFORM | ? | Finance | TRUE | |
| ARC RIG | TRUE | Rust | Low Level Infra, Speed, Trading | TRUE | TRUE |
| Base Agent Kit | TRUE | Python, Typescript | Blockchain Transactions | FALSE | |
| Crew AI | TRUE | Python | Agent Dev Kit | Non Crypto | |
| Griffain | NO CODE PLATFORM | ? | ? | ||
| LangGraph | TRUE | Python | Agent Dev Kit | Non Crypto | |
| Loria | IN DEV | ? | INDIRECT | ||
| Morpheus | TRUE | ? | TRUE | ||
| Pippin | TRUE | Python | TRUE | ||
| Solana Agent Kit | TRUE | Typescript | Blockchain Transactions | FALSE | |
| Vercel AI SDK | TRUE | Typescript | Agent Dev Kit | Non Crypto | |
| Virtuals | TRUE | Python | Ecosystem, aiXBT | TRUE | |
| Zerebro | TRUE | Python | AI Artists | TRUE |
Best Practices
When building applications with LLMs, first build the simplest solution possible, and only increase complexity when needed. You might not need an agentic system. Agentic systems often trade latency and cost for better task performance, you need to calculate when this trade-off makes sense.
When more complexity is warranted, workflows offer predictability and consistency for well-defined (STANDARDIZED) tasks, whereas agents are the better option when flexibility and model-driven decision-making are needed at scale.
For most applications optimizing single LLM calls with retrieval and in-context examples is usually enough.
Evaluation Checklist
Standard checklist for researching and comparing platforms for developing and launching crypto+ai agents. Also see blockchain and web3 game titles for similar evaluation checklists.
Compare against building agents with No Framework
Scorecard
| Focus | Score | Notes |
|---|---|---|
| Leadership Team | ?/5 | |
| Tokenomics | ?/5 | |
| Character (Personality) Development | ?/5 | |
| Capabilities (executable behaviors-actions) | ?/5 | |
| Clients (platform connectors - X) | ?/5 | |
| Providers (contextual information services) | ?/5 | |
| Evaluators (conversation analysis modules) | ?/5 | |
| Developer Depth | ?/5 | |
| Security | ?/5 | |
| Roadmap and Upgrade Pathway | ?/5 |
Is it worth investing time and effort into learning a framework for building agents? What are critical differentiators?
Leadership Team
Can they be trusted as good humans?
- Check their Twitter, Discord, Website, and other socials
- Are the founders publicly identified?
- How clear and consistent is communication of North Star?
- How aligned are developers and business development behind this vision and mission?
- Is the team present and responsive?
- Do community members seem real and engage with sustained excitement?
- Does their website explain what they do in a way you understand?
Trust and Security
Trust and Security
- TEE
- Data Integrity
Tokenomics
- What is the token utility, market cap, volume, and liquidity?
- Can you buy and sell the token?
- Is the token listed on CoinGecko and CoinMarketCap?
- Is the token listed on exchanges?
- Is there fair and healthy distribution of tokens allocation?
Evolution Tracking
- Subject Matter Expertise
- Agent personality profiling
- Cross-chain identity anchoring
- Continuous learning feedback loops
- Governance layer integration
- Agent performance base-lining
Character Development
Character Personality
- Assess knowledge ingestion tools (Eliza's folder2knowledge)
- Evaluate persona templating systems
- Test cross-platform behavior consistency
Model Data Context Management
Data and Context.
- Model Context Protocol Integration
- Map supported file formats/APIs
- Vector DB Providers
- Validate context window management
Capabilities
Tools and Actions.
- Crypto Payments
- Ecommerce
Communication Layer
Communication Layer Setup
- Implement Twitter/Telegram webhooks
- Configure on-chain interaction modules
- Test multi-channel response coherence
Roadmap and Upgrading
Roadmap towards decentralised AI
- Open Data, Access to training data and reasoning logs, with limited external auditability.
- Decentralized Inference, Transparent model execution through zkML/opML, allowing community verification.
- Decentralized AI OS, Fully autonomous agents with observable resource management, auditable decisions, and independent runtimes.
Developer Experience
Developer Experience Audit
- Documentation and Onboarding
- One way flow
- Single source of truth
- Measure setup time for new developers
- Evaluate debugging tool effectiveness
- Test CI/CD pipeline integration
Partnerships
Key partnerships that can add to Network Effects.
Point of Difference
What the key Points of Difference?
- Deep Vertical Integration
- Specialized Hardware
- Other features...