Your AI Engineering Lead
in the Terminal
Code faster with 10 AI models, persistent memory, and Agent Cloud integration. The AI coding assistant that actually remembers your stack.
Get started in seconds
npx @ainative/cody-clibrew install ainative/tap/codycurl -fsSL https://ainative.studio/install-cody.sh | shEverything you need, nothing you don't
A complete AI engineering environment that runs where you already work.
10 AI Models
From fast 2B to powerful 32B coding and reasoning models. Switch models mid-session with a single flag.
Built-in Tools
Read, Write, Edit, Bash, Glob, Grep — no plugins needed. Full filesystem access out of the box.
MCP Support
Connect to any MCP server for extended capabilities. Database, memory, APIs — all composable.
TDD Enforced
Built-in skills for test-driven development. Write tests first, then implement — enforced by default.
Multi-Platform
macOS, Linux, native binaries, or via npm. Works wherever you have a terminal.
Secure by Design
Sandboxed execution, permission-based tool access, and full audit logs for every action taken.
What makes Cody different
Cody is built on AINative infrastructure — not a thin wrapper on top of a third-party API.
ZeroDB Persistent Memory
ExclusiveCody remembers across sessions. Every decision, every pattern, every codebase convention — stored in ZeroDB and recalled automatically. No more re-explaining your stack every session.
ZeroMemory docs →- Multi-tier cognitive memory: working, episodic, semantic
- Automatic memory consolidation and decay scoring
- GraphRAG hybrid search across your entire history
- Shared memory across team members on Business/Enterprise
Agent Cloud Integration
EnterprisePromote Cody tasks to cloud-scale. Kick off long-running jobs from your terminal, monitor them from anywhere, and let Agent Cloud handle parallelization and retry logic.
Agent Cloud docs →- Deploy terminal tasks to managed agent infrastructure
- A2A networking: coordinate Cody with other agents
- Auto-scaling — run 100 tasks in parallel
- Full observability: traces, logs, and cost breakdowns
See it in action
def is_prime(n: int) -> bool:
if n <= 1:
return False
if n <= 3:
return True
if n % 2 == 0 or n % 3 == 0:
return False
i = 5
while i * i <= n:
if n % i == 0 or n % (i + 2) == 0:
return False
i += 6
return True10 models, zero config
Switch between code, general, and reasoning models with a single flag. All hosted on AINative infrastructure — no third-party API keys needed.
| Model | Size | Category | Speed |
|---|---|---|---|
| qwen-coder-32b(default) | 32B | Code | Default |
| qwen-coder-7b | 7B | Code | Fast |
| qwen-coder-3b | 3B | Code | Fastest |
| nouscoder-14b | 14B | Code | Medium |
| gemma-9b | 9B | General | Medium |
| gemma-2b | 2B | General | Fastest |
| deepseek-r1-distill-qwen-7b | 7B | Reasoning | Medium |
| deepseek-r1-distill-qwen-14b | 14B | Reasoning | Medium |
| deepseek-r1-distill-llama-8b | 8B | Reasoning | Medium |
| deepseek-r1-distill-llama-70b | 70B | Reasoning | Powerful |
All models available on Business and Enterprise plans. Model configuration docs →
Built for engineering teams
Cody is available on Business and Enterprise plans. Both include full ZeroDB memory, all 10 models, and MCP support.
Business
Cody AI agent included
For teams that ship fast with AI-assisted engineering.
- Full Cody CLI access
- ZeroDB persistent memory
- 10 AI coding models
- Team-shared memory context
- MCP server integrations
- Priority support
Enterprise
Cody + Agent Swarm
For engineering organizations running AI-native at scale.
- Everything in Business
- Agent Swarm orchestration
- Agent Cloud integration
- A2A networking
- Custom model deployment
- Dedicated SLA + support
See full plan comparison on our pricing page
Start building with Cody
One command to install. Your code context remembered forever.
npx @ainative/cody-cli