Context Engineering
Managing what information an agent sees in its context window. As of 2026-11-21, 1,466 indexed products match this subcategory (639 with full profiles); 480 were published in the last 90 days, against 350 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, ponytail leads, holding 9% of the stars of the 1,292 products here with their own repository. The most common form is MCP servers (67% of indexed products).
SubcategorySegment label: Crowded, slowing DER
Segment statistics
Whole catalogue (all 1,466 indexed products, not only profiled ones). Calculated 2026-11-21.
Crowded, slowing. Among the largest fifth of nodes at its level, but its launches grew more slowly than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.028, attention is spread as if across about 36 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 978 | 66.7% | 303 |
| Rules packs | 220 | 15.0% | 89 |
| Agent skills | 70 | 4.8% | 68 |
| Infrastructure | 68 | 4.6% | 68 |
| Plugins | 54 | 3.7% | 37 |
| Frameworks | 23 | 1.6% | 23 |
| Agent projects | 22 | 1.5% | 20 |
| Libraries | 10 | 0.68% | 10 |
| Developer tools | 8 | 0.55% | 8 |
| Platforms | 4 | 0.27% | 4 |
| SaaS products | 3 | 0.20% | 3 |
| IDE extensions | 3 | 0.20% | 3 |
| AI APIs | 2 | 0.14% | 2 |
| Protocols & standards | 1 | 0.07% | 1 |
5 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Agent MemoryPersistent memory that lets agents remember across sessions. | 804 | 316 | 312 | Crowded, slowing |
| Instruction ManagementManaging rules files, system prompts and reusable instructions. | 348 | 157 | 73 | Crowded, slowing |
| Context CompressionShrinking prompts and history to fit more into fewer tokens. | 54 | 28 | 17 | Lagging the catalogue |
| Repository IndexingIndexing codebases for semantic search and retrieval. | 30 | 15 | 5 | Thin |
| Knowledge SynchronizationKeeping agent knowledge and docs in sync with their sources. | 1 | 1 | 0 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled products only (639 of 1,466), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | ponytailMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. | Agent skill | DietrichGebert | 196k | 23d ago | MIT | ||
| 2 | claude-memPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More | Agent skill | thedotmack | 119k | today | Apache-2.0 | ||
| 3 | RAGFlowSelf-hostable RAG engine with deep document parsing, template-based chunking, citations and an agent builder. | Framework | infiniflow | 94k | 1d ago | Apache-2.0 | ||
| 4 | MiroFishA Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物 | Infrastructure | 666ghj | 86k | 1mo ago | AGPL-3.0 | ||
| 5 | claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev. | MCP server | ruvnet | 82k | today | MIT | ||
| 6 | Prompt-Engineering-Guide🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. | Agent project | dair-ai | 80k | 8mo ago | MIT | ||
| 7 | system_prompts_leaksLeaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily. | Agent project | asgeirtj | 72k | today | CC0-1.0 | ||
| 8 | Mem0Memory layer that extracts, stores and retrieves long-term facts about users and sessions for agents, available as an open-source library or hosted platform. | Library | Mem0 | 69k | 3d ago | Apache-2.0 | ||
| 9 | claude-code-best-practicefrom vibe coding to agentic engineering - practice makes claude perfect | Agent skill | shanraisshan | 69k | today | MIT | ||
| 10 | WarpOpen-source 'agentic development environment' built around a modern terminal, with a Warp Agent CLI, cloud agents run from triggers and APIs, and Warp Factories, configurable through rules, AGENTS.md, SKILL.md skills and MCP servers. | Platform | Warp | 66k | today | AGPL-3.0 | ||
| 11 | Context7Service and MCP server that fetch up-to-date, version-specific library documentation and code examples into an agent prompt. | Developer tool | upstash | 65k | 1d ago | MIT | ||
| 12 | ai-agent-book《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码 | Agent project | bojieli | 59k | 1mo ago | Apache-2.0 | ||
| 13 | agentsPlugins, agents, skills, and commands for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi, written once in Markdown and adapted to each tool by generators with validation and evals. | Agent skill | wshobson | 43k | 3d ago | MIT | ||
| 14 | OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | Infrastructure | volcengine | 43k | today | AGPL-3.0 | ||
| 15 | tidbTiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling. | Infrastructure | pingcap | 41k | today | Apache-2.0 | ||
| 16 | PageIndex📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG | Agent project | VectifyAI | 41k | today | MIT | ||
| 17 | book-to-skillTurn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work. | Agent skill | virgiliojr94 | 39k | 1d ago | MIT | ||
| 18 | LangfuseOpen-source LLM engineering platform for tracing, prompt management, evaluations and datasets, self-hosted or Langfuse Cloud. | Developer tool | ClickHouse (Langfuse) | 38k | today | MIT | ||
| 19 | context-modeFree, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OMP, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry. | MCP server | mksglu | 34k | today | — | ||
| 20 | CogneeMemory engine that turns documents and conversations into a knowledge graph plus vector index, exposed through add/cognify/search operations. | Library | topoteretes | 33k | 1d ago | Apache-2.0 | ||
| 21 | GraphitiPython library for building temporally aware knowledge graphs from episodes of data, with hybrid semantic, keyword and graph search for agent memory. | Library | Zep AI | 33k | 1d ago | Apache-2.0 | ||
| 22 | SupermemoryMemory and context API that ingests content and user interactions and serves relevant memories to LLM applications; also has a consumer app. | API | Supermemory | 32k | today | MIT | ||
| 23 | SerenaCoding-agent toolkit that uses language servers for symbol-level code retrieval and editing, exposed over MCP. | Developer tool | Oraios AI | 32k | 2d ago | GPL-3.0-or-later | ||
| 24 | RepomixCLI that packs a repository into a single AI-friendly file with token counts, ignore rules and optional Tree-sitter compression. | Developer tool | Repomix (yamadashy) | 29k | today | MIT | ||
| 25 | planning-with-filesPersistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents. | Agent skill | OthmanAdi | 28k | today | MIT | ||
| 26 | HaystackPython framework for composing pipelines and agents from components for retrieval, generation and tool use, aimed at production RAG and search. | Framework | deepset | 27k | today | Apache-2.0 | ||
| 27 | AGENTS.mdConvention for a Markdown file at the root of a repository that gives coding agents project-specific instructions such as build, test and style rules. | Protocol | Agentic AI Foundation (Linux Foundation) | 26k | 2mo ago | MIT | ||
| 28 | agency-agents-zh🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计)。搭配编排器 agency-orchestrator,一句话即可让多位专家按 DAG 自动协作。 | Rules pack | jnMetaCode | 22k | 3d ago | MIT | ||
| 29 | elephant-goldfish-modelOpen-source plugin for designing and reviewing software with agents | Agent skill | 22k | 1d ago | Apache-2.0 | |||
| 30 | lemo-opuscarA toolbox of film styles made in code for Claude Code: 99 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. · 一套用代码做片的风格工具箱:99 种现成风格,也能做出你自己的 | Agent skill | lemomo-ai | 19k | 1d ago | — | ||
| 31 | XERJThe search engine for AI agents: cited answers from your local code, docs, specs and logs. | MCP server | xerj-org | 19k | today | Apache-2.0 | ||
| 32 | WrenAIGenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more. | Agent project | Canner | 18k | 1d ago | — | ||
| 33 | MemoriMemori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises. | Infrastructure | MemoriLabs | 18k | 1mo ago | — | ||
| 34 | memvidMemory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory. | Infrastructure | memvid | 17k | 4mo ago | Apache-2.0 | ||
| 35 | semanticaGraph-Native Semantic Layer for Trustworthy Enterprise AI | Infrastructure | semantica-agi | 15k | 4d ago | MIT | ||
| 36 | EverOSOne portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. | Infrastructure | EverMind-AI | 14k | 1d ago | Apache-2.0 | ||
| 37 | Claude ContextMCP server that indexes a codebase into a vector database for semantic code search by coding agents. | Developer tool | Zilliz | 13k | 9d ago | MIT | ||
| 38 | MemOSSelf-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support. | Agent project | MemTensor | 12k | 1d ago | Apache-2.0 | ||
| 39 | cocoindexIncremental engine for long horizon agents 🌟 Star if you like it! | Agent project | cocoindex-io | 12k | today | Apache-2.0 | ||
| 40 | Trail-CodeOne shared memory for every coding agent on your team. Claude Code, Cursor and Codex get a map of your code and your team's past decisions, so they pick up where you left off. | MCP server | trailhq | 11k | today | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
Launches per month
New Context Engineering products per monthSRC
Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-12 | 3 |
| 2025-01 | 2 |
| 2025-02 | 9 |
| 2025-03 | 11 |
| 2025-04 | 8 |
| 2025-05 | 6 |
| 2025-06 | 7 |
| 2025-07 | 11 |
| 2025-08 | 14 |
| 2025-09 | 15 |
| 2025-10 | 16 |
| 2025-11 | 14 |
| 2025-12 | 20 |
| 2026-01 | 30 |
| 2026-02 | 78 |
| 2026-03 | 128 |
| 2026-04 | 112 |
| 2026-05 | 97 |
| 2026-06 | 96 |
| 2026-07 | 147 |
| 2026-08 | 130 |
| 2026-09 | 137 |
| 2026-10 | 191 |
| 2026-11 | 114 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
| Opportunity | Competition | Confidence | Score |
|---|---|---|---|
| Coverage gap: Knowledge SynchronizationKnowledge Synchronization | Low | Low | 58.9 |
| Coverage gap: Repository IndexingRepository Indexing | High | Low | 54.3 |
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .