AISmush — The AI Coding Cost Killer

Game Changer

AI-Generated Project Agents

One command scans your codebase, sends it to AI for deep analysis, and generates Claude Code agents customized to YOUR project — your patterns, your frameworks, your architecture.

Not generic templates. Agents that know your specific file structure, your naming conventions, your test framework, your build commands.

Scans your codebase in seconds
5-7 AI calls for deep analysis (~$0.03)
Generates agents, skills, and CLAUDE.md
Each agent assigned the cheapest model that can do the job
Resumes where it left off if interrupted

$ aismush --scan

# Analyzing your codebase...
Detected: Rust + TypeScript + React
Type: fullstack web app (complex)

# Generating project-specific agents:
├─ rust-expert (sonnet) ✓
├─ frontend-engineer (sonnet) ✓
├─ test-runner (haiku) ✓
├─ debugger (sonnet) ✓
└─ explorer (haiku) ✓

Created 5 agents, 8 skills, CLAUDE.md

Core Feature

Smart Model Routing + Blast-Radius Analysis

AISmush automatically detects what kind of work each turn requires and routes it to the cheapest model that can handle it — across every provider you have configured.

Routes across Claude, DeepSeek, OpenRouter (290+ models), and local servers: Ollama, LM Studio, llama.cpp, vLLM, Jan. Planning and architecture? Claude. Tool results and edits? Local Ollama — free.

Zero latency overhead — pure heuristic routing
Claude for reasoning, local models for execution
Blast-radius aware — parses imports to know which files are critical
Editing a shared type? Claude. Editing a leaf file? Ollama (free).
Automatic failover between providers
Error recovery detection (3+ errors → Claude)

# What happens behind the scenes:

"Plan the auth system" → Claude ($0.45)
Tool result: Read file → Ollama (free)
Tool result: Edit file → Ollama (free)
Tool result: Run tests → DeepSeek ($0.001)
"Debug this error" → Claude ($0.12)
Tool result: Grep → Ollama (free)

Session: $0.58 instead of $12.40

Biggest Token Saver

Structural Summarization — 3-5x Fewer Tokens

The biggest single improvement to token usage. Older tool results in your conversation get replaced with compact structural summaries — just function signatures, type definitions, and imports.

Your last 4 messages stay fully intact. Only older code results get summarized. JSON, YAML, and error results are never touched.

200-line file becomes ~30 lines (3-5x reduction)
Saves thousands of tokens per request in long sessions
Content-type aware — only summarizes code, never data
Supports Rust, TypeScript, Python, Go, and more
Combined with standard compression: 60-80% total reduction

# Old message tool_result (6,000 tokens):
use std::collections::HashMap;
use crate::db::Db;
// ... 180 lines of implementation ...
// comments, function bodies, tests ...

# After structural summary (1,200 tokens):
[Structural summary (200 lines -> 28 lines)]
use std::collections::HashMap;
use crate::db::Db;
pub struct ProxyState { ... }
impl ProxyState { ... }
pub async fn handle() -> Response { ... }
fn compress_text() -> String { ... }

5x reduction. API surface preserved.

Upgraded

Advanced Context Compression

Three layers of compression that work together — and now active in ALL modes, including Claude-only.

Command-specific patterns — cargo test output compressed from 50 lines to 2. Same for git status, git diff, git log, npm, docker
File caching — read a file once, re-reads cost ~10 tokens instead of ~2,000 (99% savings on repeated reads)
Content-type aware — code (strip comments), JSON (never touch), logs (deduplicate)
Works in ALL modes — even direct Claude-only
Never corrupts data formats or error output

# cargo test output (50 lines → 2):
Compiling... Finished... Running...
test foo ... ok
test bar ... ok
(48 more lines)

running 51 tests — all passed
test result: ok. 51 passed

# File re-read (2,000 tokens → 10):
fn main() { ... 200 lines ... }

[File unchanged — cached]

99% saved on re-reads. 95% on CLI output.

Nobody Has Solved This

Deep Memory — Full Conversation Capture

Every developer's frustration: "I already told you this yesterday."

Other tools remember tool names. AISmush captures entire conversations — your questions, the AI's answers, the reasoning, the decisions. Searchable by meaning, not just keywords.

Full conversation capture (not just tool names)
Local semantic search — MiniLM-L6-v2, ~10ms, no cloud
"auth bug" finds conversations about "JWT validation"
Search via dashboard, CLI, or API
Auto-injects relevant past context into new sessions
Configurable retention (30 days default, or forever)

$ aismush --search "auth token bug"

# Found 3 relevant conversations:

1. [3 days ago] score: 0.92
  You: "Fix the JWT token expiry bug"
  AI: "The issue is in validate_token().
      The expiry check uses > instead of >=..."
  Tools: Read(jwt.rs), Edit(jwt.rs), Bash(cargo test)

2. [5 days ago] score: 0.87
  You: "Add refresh token support"
  AI: "I'll create a refresh endpoint that..."
  - Added WebSocket broadcast server

Reliability

Context Window Management

Claude handles 200K tokens. DeepSeek handles 64K. Long sessions blow past DeepSeek's limit, causing failures and lost work.

AISmush automatically manages the mismatch. Old tool results get trimmed, large contexts route to Claude, and your work is never blocked.

Under 55K: both providers work fine
55-64K: trim old tool results for DeepSeek
Over 64K: auto-route to Claude (200K window)
Never breaks tool_use/tool_result pairing

# Context growing during long session:

Turn 1: 5K tokens → DeepSeek ✓
Turn 10: 25K tokens → DeepSeek ✓
Turn 20: 48K tokens → DeepSeek ✓
Turn 25: 58K tokens → compress + DeepSeek ✓
Turn 30: 72K tokens → auto-route to Claude ✓

# Without AISmush: DeepSeek fails at 64K.
# With AISmush: seamless handoff.

Transparency

Real-Time Cost Dashboard

See exactly what you're saving. Every request tracked: which provider, how many tokens, what it cost, what it would have cost on Claude alone.

Live dashboard at localhost:1849/dashboard
Per-request cost breakdown by provider
Savings: routing + compression + file caching combined
Date filtering — Today, 7 days, 30 days, or custom range
Request history, memory viewer, semantic search
Stats persist across sessions in SQLite

Session Stats

Requests: 142
Claude turns: 12 (planning/debugging)
DeepSeek turns: 130 (execution)

Actual cost: $1.82
All-Claude cost: $18.40
Saved: $16.58 (90.1%)

UPGRADED

Plan Orchestrator — DAG-Based Parallel Execution

Ask Claude to make a plan, then say "run plan". AISmush builds a dependency graph, maps each step to a specialized agent, and executes with maximum parallelism. Steps unblock individually — no waiting for entire waves to finish.

DAG execution — Step 3 starts the moment Step 1 finishes, without waiting for unrelated Step 2
Default: independent — steps run in parallel unless they explicitly depend on each other
Maps steps to specialized agents (rust-expert, data-engineer, etc.)
Persistent progress tracking — survives session interruptions
Context from completed steps feeds forward automatically
Verifies results with cargo check/test after completion

You: make a plan to add auth

Claude writes plan with 5 steps...

You: run plan

PLAN: Add authentication (5 steps)
Step 1 → rust-expert (no deps — ready)
Step 2 → data-engineer (no deps — ready)
Step 3 → backend-engineer (after 1)
Step 4 → backend-engineer (after 2, 3)
Step 5 → test-runner (after 4)

Execute this plan? [Go / No]

Stop Burning Money on AI Coding

Multi-Provider Routing + Advanced Compression

Claude Code is incredible. The bill isn't.

Eight Weapons Against Token Waste

AI-Generated Project Agents

Smart Model Routing + Blast-Radius Analysis

Structural Summarization — 3-5x Fewer Tokens

Advanced Context Compression

Deep Memory — Full Conversation Capture

Context Window Management

Real-Time Cost Dashboard

Plan Orchestrator — DAG-Based Parallel Execution

Three Steps. That's It.

Install

Scan

Code

CLI Reference

Running

Setup & Configuration

Tools

Maintenance

Environment Variables

Three Ways to Run

Smart Routing (Default)

Local + Cloud (Best Savings)

Direct Mode (Claude Only)

Install in 10 Seconds

What's Coming Next

Team Dashboard

Cost Budgets

Model Benchmarking