14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

python tree-sitter developer-tools llm-tools llm-compression prompt-compression context-compression ai-infrastructure ai-agent-tools token-compression context-pruning context-window-optimization openclaw llm-token-compression llm-cost-reduction llm-context-compression claw-compactor reversible-compression ast-code-analysis fusion-pipeline

• Updated Apr 1, 2026
• Python

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

typescript cordis ai-agent llm llm-agent context-window deepseek context-management prompt-compression agent-tools llm-cost ai-coding token-optimization token-efficiency coding-agent context-engineering context-pruning deepseek-harness tool-output dsh-plugin

• Updated Nov 1, 2026
• TypeScript

Staged context pruning for OpenCode, Oh My Pi, pi, and Claude Code.

plugin ai opencode pi compact ai-agents compaction context-management context-compression claude-code coding-agent muilt-agents context-engineering context-pruning claude-code-plugin opencode-plugin

• Updated Oct 12, 2026
• TypeScript

Biological code organization system with 1,029+ production-ready snippets - 95% token reduction for Claude/GPT with AI-powered discovery & offline packs

developer-tools code-snippets code-organization cost-reduction token-reduction prompt-optimization context-management ai-assisted-coding context-compression rag-optimization chain-of-draft token-optimization llm-efficiency claude-optimization context-engineering context-pruning repository-aware gpt-optimization infinite-retrieval llm-context-window

• Updated Nov 10, 2025
• Python

Pi extension for dynamic context pruning

compression pi context-pruning pi-coding-agent pi-extension pi-package pi-dcp

• Updated Oct 22, 2026
• TypeScript

Self-hosted gateway for LLMs and decision models. Claude Code, Codex, OpenCode and any OpenAI/Anthropic SDK app reach any provider (OpenRouter, Groq, Ollama…) with context pruning; Jev and open-rlcd System One decisions get audit and calibration. Live dashboard, single Go binary.

golang mcp opencode self-hosted openai codex anthropic openrouter ollama llm-proxy ai-gateway coding-agents llm-observability llm-gateway claude-code token-optimization decision-models context-pruning jev open-rlcd

• Updated Sep 24, 2026
• Go

Local gateway that prunes Claude Code's API context in-flight — dedup, purge failed calls, trim bloat, strip old screenshots. Anthropic-sanctioned (ANTHROPIC_BASE_URL), no CA cert, no restart.

rust cli proxy gateway claude llm prompt-caching anthropic claude-code context-pruning

• Updated Oct 1, 2026
• Rust

the research synthethizer outer loop

compression ml ensemble-machine-learning modernbert context-pruning loop-engineering

• Updated Nov 4, 2026
• Python

Reversible context pruning for Pi, powered by TypeSafe Jev. Keep useful context without deleting session history.

typescript pi typesafe context-pruning pi-extension pi-package jev

• Updated Sep 18, 2026
• TypeScript

You approve the plan. CodeBOT does the rest. Semi-autonomous multi-agent development: plan first, execute fully, report every change. Currently built for Copilot & Codex.

nodejs skills skill developer-tools copilot harness codex ai-agents cli-tool codebot dynamic-workflows github-copilot openai-codex cost-reduction llm-orchestration agentic-workflow copilot-extension custom-agents context-pruning copilot-sdk

• Updated Nov 9, 2026
• JavaScript

High-Speed, Zero-Dependency Cognitive Deadlock & Oscillation Interceptor for Autonomous AI Coding Agents.

python deadlock-detection self-healing autonomous-agents ai-agents runtime-verification llm meta-ai agentic-ai swe-bench context-pruning

• Updated Nov 5, 2026
• Python

Local-first, source-backed memory layer for coding agents with an installer for eight harnesses and reversible /prune

python coding-agents agent-memory context-pruning jev complete-tech-ai-research

• Updated Nov 7, 2026
• Python

Capability-aware context-pruning installer and Jev assessment engine for coding agents; experimental, not live-host tested

python coding-agents context-pruning jev complete-tech-ai-research

• Updated Nov 7, 2026
• Python

DeepSeek Harness 动态上下文管理插件（Dynamic Context Pruning for dsh），对标 opencode-dcp

dsh deepseek context-management token-optimization context-pruning deepseek-harness dsh-plugin deepseek-harness-plugin

• Updated Oct 14, 2026
• TypeScript

Stop LLM context echoing, repetition spirals, and memory poisoning in multi-turn chats.

ai-agents hallucination llm prompt-compression context-pruning anti-echo

• Updated Sep 25, 2026
• Python

A model-aware harness for OpenCode: bring your own model, compile it into job lanes with measured baselines, privacy-aware routing and a verifiable install.

cli open-source node terminal opencode developer-tools harness ai-agents model-agnostic llm ai-workflow context-management context-pruning model-routing opencode-plugin reasoning-effort

• Updated Nov 8, 2026
• JavaScript

OpenCode V2 plugin: dynamic context pruning for MCP tools and skills using Jev (TypeSafe System One)

skills mcp opencode typesafe token-optimization context-pruning opencode-plugin jev

• Updated Oct 28, 2026
• TypeScript

AI-powered tutoring system for Indian state-board students. Upload textbook PDFs and get curriculum-aligned answers instantly. Uses Context Pruning to score and filter chapters before querying Gemini LLM — reducing API costs by ~80%. Built with Python, Flask, FAISS, sentence-transformers, and Gemini 2.5 Flash.

education flask ai tutor gemini-api rag faiss-vector-database context-pruning

• Updated Mar 22, 2026
• HTML

Local Ollama RAG memory proxy using ChromaDB and nomic-embed-text to retrieve relevant chat history, compress context, and reduce LLM tokens.

python self-hosted embeddings semantic-search long-term-memory rag fastapi edge-ai vector-database generative-ai chromadb local-llm ollama context-window llm-proxy llm-memory context-compression nomic-embed-text context-pruning

• Updated Jun 19, 2026
• Python

Enterprise-grade Context Pruning for RAG. Hierarchical 2-stage architecture (MiniLM-L6 ONNX INT8) achieving 60-75% token compression at <20ms latency.

python nlp information-retrieval onnx machine-learning-production rag llm-optimization context-pruning

• Updated Mar 31, 2026
• Python