Performance

Agentium is built for minimal overhead — fewer tokens, faster responses, lower cost. This page covers the key optimizations and benchmark results.

Benchmark Results

All benchmarks use gpt-4o-mini, identical prompts, and 5 runs per scenario. Agentium and LangChain run on Node.js; Agno runs on Python.

Simple Completion

Metric	Agentium	LangChain	Agno
Startup (ms)	171	301	2730
Avg Response (ms)	769	737	2077
Avg Prompt Tokens	28	28	28
Avg Total Tokens	35	35	35
Avg Cost / Run	$0.000008	$0.000008	$0.000008

Tool Calling

Metric	Agentium	LangChain	Agno
Avg Response (ms)	1617	1678	3064
Avg Prompt Tokens	167	167	173
Avg Total Tokens	196	196	202
Avg Cost / Run	$0.000042	$0.000042	$0.000043

Agentium and LangChain produce identical tool schemas (167 prompt tokens). Agentium strips verbose JSON Schema metadata ($schema, additionalProperties) to keep schemas compact.

Multi-turn Memory

Metric	Agentium	LangChain	Agno
Avg Response (ms)	2408	2324	5892
Avg Prompt Tokens	189	309	94
Avg Completion Tokens	30	57	66
Avg Total Tokens	219	366	160
Avg Cost / Run	$0.000046	$0.000081	$0.000054

Agentium uses 39% fewer prompt tokens and 43% less cost than LangChain for multi-turn conversations. LangChain injects heavier system prompts and history formatting overhead.

Summary

Scenario	Fastest	Fewest Tokens	Cheapest
Simple Completion	LangChain (737ms)	Tied (35)	Tied
Tool Calling	Agentium (1617ms)	Agentium (196)	Tied
Multi-turn Memory	LangChain (2324ms)	Agno (160)	Agentium ($0.000046)

Agentium is the fastest for tool calling, the cheapest for multi-turn conversations, and matches LangChain on tool schema efficiency. Response latency is within noise across simple completions.

Optimizations

Tool Schema Caching & Optimization

Tool definitions (Zod-to-JSON Schema conversion) are computed once at agent construction and cached. Verbose JSON Schema metadata ($schema, additionalProperties, description on the root object) is stripped automatically — reducing token overhead without losing semantic information.

const agent = new Agent({
  name: "bot",
  model: openai(process.env.OPENAI_MODEL ?? "gpt-6.1-sol"),
  tools: [weatherTool, searchTool],
});

For OpenAI models, tools can opt into strict mode for guaranteed valid JSON output:

const weatherTool = defineTool({
  name: "getWeather",
  description: "Get weather for a city",
  parameters: z.object({ city: z.string() }),
  execute: async ({ city }) => `Sunny in ${city}`,
  strict: true, // enables OpenAI Structured Outputs on this tool
});

Automatic Retry

Transient LLM API failures are automatically retried with exponential backoff + jitter. Retryable errors include HTTP 429, 5xx, and network errors.

const agent = new Agent({
  name: "reliable-bot",
  model: openai(process.env.OPENAI_MODEL ?? "gpt-6.1-sol"),
  retry: {
    maxRetries: 5,
    initialDelayMs: 1000,
    maxDelayMs: 30000,
  },
});

Default: 3 retries, 500ms initial delay, 10s max delay.

Token-Based History Trimming

Trim history on memory, not on Agent:

const agent = new Agent({
  name: "bot",
  model: openai(process.env.OPENAI_MODEL ?? "gpt-6.1-sol"),
  memory: {
    storage: new InMemoryStorage(),
    maxMessages: 50,   // keep last N messages
    maxTokens: 8000,   // or trim by tokens
  },
});

There is no maxContextTokens on Agent.

Background extraction

When memory.userFacts (or profile / entities / learnings) is on, extraction runs after the answer is sent. The user is not waiting on it. Tiny always-on notes (fileMemory) are injected into the prompt instead of being fetched as a tool.

Streaming Usage Tracking

Token usage (promptTokens, completionTokens, totalTokens, reasoningTokens) is accurately tracked in both run() and stream() modes. Stream usage is accumulated from provider finish chunks.

Methodology

All benchmarks use gpt-4o-mini with identical prompts
Each scenario runs 5 times; results are averaged
Startup time measures framework import + agent initialization
Cost uses gpt-4o-mini pricing: $0.15/1M input,$ 0.6/1M output
Network latency to OpenAI is shared across all frameworks
Full benchmark scripts are in benchmarks/ in the repository

Reference

Package APIs

Type guides

Upgrades

Architecture and tooling

Benchmark Results

Simple Completion

Tool Calling

Multi-turn Memory

Summary

Optimizations

Tool Schema Caching & Optimization

Automatic Retry

Token-Based History Trimming

Background extraction

Streaming Usage Tracking

Methodology

​Benchmark Results

​Simple Completion

​Tool Calling

​Multi-turn Memory

​Summary

​Optimizations

​Tool Schema Caching & Optimization

​Automatic Retry

​Token-Based History Trimming

​Background extraction

​Streaming Usage Tracking

​Methodology

Benchmark Results

Simple Completion

Tool Calling

Multi-turn Memory

Summary

Optimizations

Tool Schema Caching & Optimization

Automatic Retry

Token-Based History Trimming

Background extraction

Streaming Usage Tracking

Methodology