Results for “token-optimization”

Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.

Orchestrate expensive frontier models as reviewers and cheaper subagents for bounded, token-heavy work to optimize cost and quality.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Optimize context usage for the session by reducing bloat, improving token efficiency, and focusing on relevant areas. Use when context is growing large, responses are slow, or switching between unrelated tasks. Covers context analysis, compacting, targeted pruning, MCP-first strategies, and focused scoping by area.

Reduces AI API costs by 30-75% by classifying task complexity, checking prompt quality, and routing tasks to the most cost-efficient model tier before execution.

Transform the agent into a performance engineer. Apply methodologies for measuring, profiling, and optimizing code (caching, algorithm complexity, resource usage).

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

Evaluates Base ERC-20 tokens by contract address, returning a 0-100 score across five criteria, launch protocol classification, security flags, and a narrative interpretation.

Designs, optimizes, and evaluates prompts for LLMs, including structured outputs, chain-of-thought, and evaluation frameworks.

Token-efficient code review using Tree-sitter AST graphs and MCP. Reduces AI assistant token usage by 6.8–49x by computing blast radius of changes instead of reading entire codebases. Uses SQLite graph database for structural analysis.

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

Standards for creating new High-Density Agent Skills with optimal token economy.

Builds a local knowledge graph of a codebase using tree-sitter and graph algorithms, then answers architecture questions by querying the graph instead of reading many files, saving tokens.

Mine BOTCOIN tokens by solving AI-generated challenges and submitting on-chain proofs on Base.

Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust the savings.

Optimizes Dify workflows and plugins by restructuring graphs, reducing LLM token usage, tuning worker pools, and improving parallel processing.

Reduce per-token latency on Jetson vLLM servers by appending speculative decoding configuration, with guidance on when to enable and how to benchmark the improvement.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.