RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
{
"name": "Synap",
"url": {
"default": "https://pool.linkrra.com/v1"
},
"url_suffix": {
"chat": "chat/completions",
"models": "models"
},
"class": "synap",
"models": [
{
"name": "gpt-oss-20b",
"context_length": 131072,
"max_output": 131072,
"model_types": [
"chat"
],
"tools": {
"support": true
}
},
{
"name": "gemma-4-26b-a4b-it",
"context_length": 131072,
"max_output": 131072,
"model_types": [
"chat"
],
"tools": {
"support": true
}
},
{
"name": "qwen3-coder-30b",
"context_length": 98304,
"max_output": 98304,
"model_types": [
"chat"
],
"tools": {
"support": true
}
},
{
"name": "qwen/qwen3-30b-a3b",
"context_length": 98304,
"max_output": 98304,
"model_types": [
"chat"
],
"tools": {
"support": true
}
},
{
"name": "qwen/qwen3-vl-30b-a3b-instruct",
"context_length": 65536,
"max_output": 65536,
"model_types": [
"chat",
"vision"
],
"tools": {
"support": true
}
}
]
}