The runtime amplification layer for AI coding agents. Five deterministic Claude Code hooks that don't just block — they amplify.
Hooks for Claude Code, Cursor, GitHub Copilot, LangGraph, CrewAI, AgentScope, and LangChain. Zero extra LLM calls. Zero network. AGPL-3.0. Built to compose with SuperLocalMemory as the default memory provider — runtime amplification meets local-first memory.
Agent Amplifier ships SuperLocalMemory as its default memory provider. Each amplification turn recalls relevant context from SLM before the host agent runs and remembers key facts at session end. Two products, one composable runtime: SLM gives the agent persistent memory, Agent Amplifier shapes how the agent uses that memory at every turn.
Reference integration: examples/slm_provider.py in the Agent Amplifier repository.
Five deterministic Python hooks that shape what the host agent does next. No extra LLM calls. Fail-open.
Deterministic complexity classifier routes each prompt to one of five effort tiers: minimal, low, medium, high, ultra. Shapes phase budget and model tier suggestion with no extra LLM call.
Re-injects the original goal every N tool calls to prevent multi-turn drift. The hook layer answer to the runaway-context problem.
Detects when agent output is substantially similar to the prior iteration. Stops the loop. Saves tokens and prevents oscillation.
Each iteration ramps audit pressure: senior engineer → adversarial reviewer → red-team auditor. Catches what single-pass review misses.
Cost-bounded amplification. Set a session budget and Agent Amplifier shapes phase prompts to stay within it — without truncating mid-task.
One install command per host. agent-amp install <host>
Also available on npm: npm install agent-amplifier
Part of the Qualixar AI Reliability Engineering platform · AGPL-3.0-or-later
