$$$$$$$\                       $$\     $$\        $$$$$$\                  $$\           
$$  __$$\                      $$ |    $$ |      $$  __$$\                 $$ |          
$$ /  \__|$$\   $$\ $$$$$$$\ $$$$$$\   $$$$$$$\  $$ /  \__| $$$$$$\   $$$$$$$ | $$$$$$\  
\$$$$$$\  $$ |  $$ |$$  __$$\\_$$  _|  $$  __$$\ $$ |      $$  __$$\ $$  __$$ |$$  __$$\ 
 \____$$\ $$ |  $$ |$$ |  $$ | $$ |    $$ |  $$ |$$ |      $$ /  $$ |$$ /  $$ |$$$$$$$$ |
$$\   $$ |$$ |  $$ |$$ |  $$ | $$ |$$\ $$ |  $$ |$$ |  $$\ $$ |  $$ |$$ |  $$ |$$   ____|
\$$$$$$  |\$$$$$$$ |$$ |  $$ | \$$$$  |$$ |  $$ |\$$$$$$  |\$$$$$$  |\$$$$$$$ |\$$$$$$$\ 
 \______/  \____$$ |\__|  \__|  \____/ \__|  \__| \______/  \______/  \_______| \_______|
          $$\   $$ |                                                                     
          \$$$$$$  |                                                                     
           \______/                                                                      

Neural Intuition x Symbolic Precision

A neurosymbolic coding platform. Six symbolic gates verify every LLM output in ~3-8ms.
The terminal is the correct interface.

---

Install

# TUI -- the full experience
npx @avasis-ai/synthcode-tui@latest

# Framework -- programmatic API
bun add @avasis-ai/synthcode

Screenshots

The Six Gates

Gate	Verifies	Latency
Structure	AST well-formedness, syntax validity	~1ms
Scope	Variable bindings, lexical resolution	~2ms
Type	Type consistency, inference chains	~3ms
Safety	Side-effect boundaries, mutation control	~2ms
Control Flow	Reachability, termination guarantees	~3ms
Semantic	Logical coherence, intent alignment	~5ms

Features

• Dual-path verification -- neural output passes six symbolic gates before touching your codebase
• Zero-dependency framework -- 10KB gzipped, no runtime deps
• Agentic chat -- up to 15 autonomous rounds with inline gate feedback
• Six screen modes -- chat, gates, code view, world model, trust boundary, playground
• Provider-agnostic -- Gemini, Groq, OpenRouter, OpenAI, Ollama
• 269 tests -- 300+ consecutive CI runs, zero failures
• OpenTUI engine -- built on Zig+TS for native terminal performance

Quick Start

TUI:

npx @avasis-ai/synthcode-tui@latest

Framework:

import { Agent, BashTool, DualPathVerifier } from "@avasis-ai/synthcode";
import { OllamaProvider } from "@avasis-ai/synthcode/llm";

const agent = new Agent({
  model: new OllamaProvider({ model: "qwen3:32b" }),
  tools: [BashTool],
  dualPathVerifier: new DualPathVerifier(),
});

for await (const event of agent.run("List all TypeScript files in src/")) {
  if (event.type === "text") process.stdout.write(event.text);
}

Architecture

  LLM Output
      |
      v
 +----------+   +-------+   +------+   +--------+   +------------+   +----------+
 | Structure|-->| Scope |--->| Type |--->| Safety |--->| ControlFlow|--->| Semantic |
 +----------+   +-------+   +------+   +--------+   +------------+   +----------|
      |                                                               |
      v                                                               v
   REJECT                                                          ACCEPT

Framework API

import {
  Agent, BashTool, FileReadTool, FileWriteTool,
  DualPathVerifier, WorldModel, CostTracker, CircuitBreaker,
  AnthropicProvider, OpenAIProvider, OllamaProvider,
} from "@avasis-ai/synthcode";

const agent = new Agent({
  model: new AnthropicProvider({ model: "claude-sonnet-4-20250514" }),
  tools: [BashTool, FileReadTool, FileWriteTool],
  dualPathVerifier: new DualPathVerifier(),
  costTracker: new CostTracker(),
});

npx @avasis-ai/synthcode "Explain this codebase"              # auto-detect
npx @avasis-ai/synthcode "Refactor this" --ollama qwen3:32b   # local
npx @avasis-ai/synthcode adapt catalog                         # 30+ models

Agent Patterns

SynthCode is designed for autonomous agents that run 24/7. Here are common patterns:

Error Handling & Resilience

Autonomous agents must handle failures gracefully:

import { createResilientTool, ErrorLogger, CircuitBreaker } from "@avasis-ai/synthcode";

// Wrap tools with retry logic and circuit breaking
const bashTool = createResilientTool(
  new BashTool(),
  new ErrorLogger(),
  new CircuitBreaker(),
  { maxRetries: 3 }
);

// The agent continues even when tools fail temporarily

See examples/error-handling.ts for a complete implementation with:

• Automatic retry with exponential backoff
• Circuit breaker pattern for failing tools
• Structured error logging for debugging
• Graceful degradation when tools are unavailable

Continuous Monitoring

Track agent performance over time:

const costTracker = new CostTracker();
const agent = new Agent({
  model: anthropic("claude-3-5-sonnet-20241022"),
  tools: [BashTool, FileReadTool],
  costTracker, // Tracks tokens, cost, and usage metrics
});

// Get stats anytime
const stats = costTracker.getStats();
console.log(`Total cost: $${stats.totalCost}`);

Memory & Context

Persistent memory for long-running agents:

import { SQLiteStore } from "@avasis-ai/synthcode/memory";

const memory = new SQLiteStore({ path: "./agent-memory.db" });

// Agent remembers conversations across restarts
const agent = new Agent({
  model: anthropic("claude-3-5-sonnet-20241022"),
  tools: [BashTool],
  memory, // Persist context to disk
});

Autonomous Loops

Run agents continuously:

import { agentLoop } from "@avasis-ai/synthcode";

for await (const result of agentLoop(agent, {
  maxTurns: 15,
  timeout: 5 * 60 * 1000, // 5 minute timeout
  onTurn: async (turn, events) => {
    // Hook into each turn for monitoring
    console.log(`Turn ${turn}:`, events.length, "events");
  }
})) {
  if (result.done) break;
  // Continue loop
}

Examples

• examples/autonomous-agent.ts - CI/CD automation and issue fixing
• examples/error-handling.ts - Resilient error handling patterns
• examples/coding-agent.ts - Codebase refactoring
• examples/basic.ts - Simple tool usage
• examples/demo.ts - Full feature demonstration

Feature Comparison

	SynthCode	Claude Code	Cursor	Aider
Symbolic verification	Yes	No	No	No
Dual-path gates	Yes	No	No	No
Zero dependencies	10KB	No	No	No
Terminal-native TUI	Yes	Yes	No	Yes
Provider-agnostic	5+	No	Partial	Partial
Open source	MIT	No	No	Apache

---

avasis-ai/synthcode -- MIT License -- Built by Avasis AI