🔓Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
// ragheadroomlabs-ai/⟨Python⟩★ 74,459◷ Apache-2.0[ claude ]
Projects tagged #context-engineering
// context-engineering (31)
🔓
🔓A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
// raggsd-build/⟨JavaScript⟩★ 64,462◷ MIT[ claude ]
🔓📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
// uncategorizedVectifyAI/⟨Python⟩★ 38,436◷ MIT[ claude ]
🔓GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted da…
// ragCanner/⟨Python⟩★ 17,750◷ NOASSERTION[ claude ]
🔓
🔓Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
// mcp-serverstrailhq/⟨TypeScript⟩★ 9,545◷ MIT[ claude ]
🔓Memory library for building stateful agents
// ragplastic-labs/⟨Python⟩★ 7,340◷ AGPL-3.0[ claude ]
🔓Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
// automationai-boost/⟨Python⟩★ 4,611◷ NOASSERTION[ claude ]
🔓
🔓Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, rem…
// mcp-serversyvgude/⟨Rust⟩★ 3,859◷ Apache-2.0[ claude ]
🔓The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a pe…
// uncategorizedpipeshub-ai/⟨Python⟩★ 3,811◷ Apache-2.0[ claude ]
🔓
🔓Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Activ…
// mcp-serversneomjs/⟨JavaScript⟩★ 3,280◷ MIT[ claude ]
🔓📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verificat…
// ragwquguru/⟨Python⟩★ 3,158[ claude ]
🔓QuantMind is an open source agent-native knowledge extraction and retrieval framework for quantitative finance.
// uncategorizedLLMQuant/⟨Python⟩★ 3,023◷ MIT[ claude ]
🔓Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
// pluginsalexgreensh/⟨Python⟩★ 2,460◷ NOASSERTION[ claude ]
🔓The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.
// uncategorizedatomicstrata/⟨TypeScript⟩★ 2,159◷ MIT[ claude ]
🔓Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and cont…
// mcp-servers2akouwu/⟨Python⟩★ 1,254◷ MIT[ claude ]
🔓Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
// mcp-serverscontext-space/⟨Go⟩★ 813◷ AGPL-3.0[ claude ]
🔓A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via…
// devtoolsmindmuxai/⟨JavaScript⟩★ 563◷ Apache-2.0[ claude ]
🔓Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessions, with knowledge graphs, hybrid search, and…
// ragMikeK184/⟨Rust⟩★ 40◷ Apache-2.0[ claude ]
🔓AI-powered file organization and context engineering that understands content, not patterns. Automatically sorts temporary scripts from permanent docs while…
// ragramakay/⟨TypeScript⟩★ 71◷ MIT[ claude ]
🔓ContextX: Context-driven AI development framework powered by Claude Code. Transform documents into complete projects with intelligent agent workflows.
// ragyzfly/⟨Shell⟩★ 66◷ Apache-2.0[ claude ]
🔓Claude Code for GTM — quickstart for GTM operators
// ragmatteotitta/⟨HTML⟩★ 61[ claude ]
🔓Automatic context preservation for Claude Code. Never lose work to compaction again. 7 hooks, 187 semantic patterns, 3 MCP tools.
// ragCapnjbrown/⟨TypeScript⟩★ 61◷ MIT[ claude ]
🔓Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local model…
// mcp-serversKerneta/⟨JavaScript⟩★ 44◷ Apache-2.0[ claude ]
🔓Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
// mcp-servers00200200/⟨Python⟩★ 11◷ MIT[ claude ]
🔓Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Ollama/VLLM/llama.cp…
// ragiKislay/⟨Python⟩★ 20◷ Apache-2.0[ claude ]
🔓The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing that never makes it…
// devtoolsKoragraph/⟨JavaScript⟩★ 14◷ NOASSERTION[ claude ]
🔓A warn-only runtime layer for Claude Code agents. Keeps feature state, scope and handoffs on disk so they survive compaction, and requires an evidence path b…
// ragRedtropig/⟨Shell⟩★ 13◷ MIT[ claude ]