5 repository-uri
Awesome GitHub RepositoriesToken Optimization Strategies
Techniques for reducing language model token consumption through result caching and state persistence.
Distinguishing note: Specifically addresses token efficiency in the context of durable workflow engines, distinct from general model caching.
Explore 5 awesome GitHub repositories matching artificial intelligence & ml · Token Optimization Strategies. Refine with filters or upvote what's useful.
Awesome Token Optimization Strategies GitHub Repositories
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- conductor-oss/conductor
conductor-oss/conductor
31,962Vezi pe GitHubConductor is a durable workflow engine designed to orchestrate complex, long-running business processes and autonomous agent loops. It functions as a stateful execution platform that persists the entire history of a process, ensuring that workflows remain reliable and recoverable across infrastructure failures, system restarts, and transient network errors. By managing task lifecycles, worker polling, and state transitions, it provides a centralized coordination layer for distributed systems. The platform distinguishes itself through its specialized support for AI agent orchestration, allowin
Persists model call results to storage to prevent redundant execution and minimize token usage during retries.
Javadistributed-systemsdurable-executiongrpc - cameron314/concurrentqueue
cameron314/concurrentqueue
12,070Vezi pe GitHubConcurrentQueue is a header-only C++ template library that provides a lock-free data structure for multi-producer multi-consumer thread communication. It functions as a synchronization primitive designed to coordinate data flow between concurrent execution units using atomic operations rather than traditional mutex locking. The library distinguishes itself through a design that minimizes contention and synchronization overhead. It utilizes sub-queue token mapping to distribute workloads across partitioned internal queues and supports bulk operations to transfer multiple data elements in singl
Assign specific tokens to threads to map them to dedicated sub-queues, reducing resource competition and increasing processing speed during high-volume data operations.
C++ - muratcankoylan/agent-skills-for-context-engineering
muratcankoylan/Agent-Skills-for-Context-Engineering
8,376Vezi pe GitHubThis project is a comprehensive framework for the orchestration, evaluation, and context management of large language model agents. It provides a set of architectural patterns and standards for designing agent interactions, integrating external tools, and establishing memory architectures to persist knowledge across sessions. The system focuses on optimizing the limited memory of language models through token-aware context compression and filesystem-based context offloading. It incorporates secure execution environments using sandboxed virtual machines and isolated containers to safely run ba
Reduces token consumption using masking and caching strategies to improve data retrieval precision.
Python - zhaochenyang20/awesome-ml-sys-tutorial
zhaochenyang20/Awesome-ML-SYS-Tutorial
5,371Vezi pe GitHubThis project provides a comprehensive technical guide and framework for engineering large-scale machine learning systems. It covers the full lifecycle of model development, focusing on the infrastructure and computational principles required to build, train, and serve generative AI models across distributed GPU clusters. The repository distinguishes itself by offering deep-dive tutorials and implementation strategies for complex system challenges. It emphasizes high-performance architectural primitives, such as collective communication orchestration, distributed tensor sharding, and static gr
Optimizes context usage by extracting incremental observation tokens to prevent redundant prompt bloating.
Python - parcadei/continuous-claude-v3
parcadei/Continuous-Claude-v3
3,531Vezi pe GitHubThis project is an agentic development framework and autonomous software engineering system. It utilizes a coordinated network of specialized LLM agents to automate the full software development lifecycle, from codebase exploration and architectural planning to implementation and automated refactoring. The system is distinguished by an agentic memory system and a test-driven development orchestrator. It maintains project continuity across sessions by capturing architectural learnings and state in a persistent semantic database and enforces code quality through an automated cycle of generating
Optimizes LLM token usage by replacing raw file content with structured summaries and call graphs.
Pythonagentsclaude-codeclaude-code-cli
