context-engineering — independent software & tools
-
codemium
Persistent coding intelligence for Codex — project-aware context, adaptive reasoning, scoped changes, and risk-aware verification.
-
aidimag
Verified memory for AI coding agents. Every memory carries evidence and is re-verified on every pull — stale beliefs get flagged, not retrieved. MCP + CLI.
-
qarinah
Your project remembers across coding agents. Compact, cited project memory for Codex, Claude Code, Cursor, and compatible tools.
-
FixMap
Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.
-
gcontext
The framework for building stateful agents. Your agent is a folder of state, served over MCP, used from any runtime.
-
archcore-prompt-studio
Top Free Context Engineering Plugin 2026 - Claude Code, Cursor & Codex Setup
-
compile-code
A compiler for AI coding tasks: pre-resolves repo facts (callers, git history, blast radius, bug-site source) before your coding agent's first token, then runs a scoped verify over exactly the lines it changed. Deterministic, local, zero model calls. Thin CLI over the roam-code engine; 22 intent procedures, 28 languages.
-
tent
用于管理你与 coding agents 之间的意图、上下文与交接流程 —— 基于 Open Knowledge Format（OKF）构建的 Obsidian plugin。
-
vibe-tent
用于管理你与 coding agents 之间的意图、上下文与交接流程 —— 基于 Open Knowledge Format（OKF）构建的 Obsidian plugin。
-
ailmanac
AILmanac — the always-current, community almanac for getting the most out of Claude and every AI. For all levels.
-
model-workspace-protocol-tool
Deterministic workspace mapper that assembles layered LLM context from your project's folder tree.
-
Progressive-Context-Kit
Token-efficient, quality-first, spec-driven development kit for AI coding agents — progressive context, durable project memory, skills, and workflows for Claude Code and Codex.
-
loadout
Equip the right context for the job — named context kits for AI coding agents, auto-equipped per stack, machine, or task
-
claude-context-lint
Audit Claude Code context usage and find wasted tokens in CLAUDE.md, skills, MCP schemas, and system prompts
-
DeepLaw
DeepLaw 2.0：本地优先单用户 Agent Knowledge OS，融合自主长期记忆、Markdown-native 知识、可信 Ledger、有界上下文与可验证法律证据。
-
llm-wiki
Build a personal wiki from your files, messages, and bookmarks using an automated LLM pipeline for knowledge management.
-
agentprobe
Test, record, and replay AI agents locally and in CI with a private pytest-style framework
-
index
Map one unfamiliar repo into a self-contained, verified wiki, or a whole workspace into a two-layer atlas of repos, docs, and dependency graphs. Built from file:line evidence, not guesses. Offline, deterministic, zero runtime dependencies, with a native MCP bridge.
-
context-kit
4 PCA templates + 5 Claude Code skills — give any AI agent deep personal context. One-command install.
-
trigger-flare
Skill Radar 2026: AI-Powered Smart Signal Triage for Claude Code
-
renma
Manage human-curated context assets for LLMs and agents in Git
-
renma
Manage human-curated context assets for LLMs and agents in Git
-
dsh-context-lens
See what every plugin puts into the model.
-
inplan
inplan — a Markdown editor for human ⇄ coding-agent planning. CLI + desktop editor.
-
commitlore
Git-native decision memory for Claude Code, Codex, Cursor and other coding agents. Preserve constraints and rejected alternatives; surface only the decisions still in force.
-
Syntavra
Adaptive context and runtime optimization for coding agents—reducing token waste, externalizing tool output, preserving exact session history, and enforcing secure tool routing.
-
leadline
Evidence router & policy engine for coding agents — enforces source choice and proof-of-use through Claude Code hooks, including routes to MCP tools. Local-first; no LLM in the hook loop.
-
khive
A knowledge graph your AI agents build, query, and grow. Built for agents that need structure beyond vectors
-
Kote
A developer memory layer that automatically captures and organizes AI sessions, Git history, and development context into searchable knowledge.
-
perseus
Live context engine and MCP server for AI agents. Resolves git, services, and tests into ready context. Local-first, MIT. PyPI: perseus-ctx.
-
tsubasa
Your engineering captain: a repo-resident AI persona with a knowledge graph stored in git. Agents cite incidents, ADRs and PRs instead of guessing — 47% fewer wrong answers, 40% cheaper on a public benchmark. Claude Code plugin + CLI.
-
ripwire
ripwire — the ripgrep of AI context. A zero-dependency C++23 CLI that maps any codebase into a ranked, deterministic call graph for coding agents: orientation, blast radius, tests-to-run and quality verbs, plus an MCP server. ripgrep-fast retrieval, a tripwire on every claim it emits.
-
bearing
An intel layer for AI coding agents that assumes its own rules might be wrong — and keeps the evidence. Authoritative north-stars the agent must cite, a task-core written before compaction eats it, review by an expert in YOUR domain, and an installer that verifies its own claims instead of printing success. Claude Code, Cursor, Zed, Codex.
-
memorize
Shared, persistent memory for AI coding agents — Claude Code & Codex share one local-first, event-sourced project brain that survives sessions and syncs across machines. No server, no API key required.
-
AIWorkHub
Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.
-
structify-dev-flow
Plan Build Run 2026: Ultimate Claude Code Plugin for Structured Agent Development
-
Repo2AI
Convert code repositories into structured, size-limited context packs for AI tools like ChatGPT, Claude, and Cursor.
-
mduct
Call MCP servers from the shell: pipe them, script them, run them by hand — and keep their tool schemas out of your LLM context. Because it glues shit together.
-
engineering-kernel
The kernel of the Engineering OS: indexes, retrieves and classifies engineering knowledge. Ships eng, the platform's CLI.
-
icm-graph-context-flow
Best Token-Efficient AI Coding Tools 2026 – Reduce Costs 90% with Local Memory & MCP
-
crux
Typed building blocks for everything around your LLM call.
-
cskill-agents
Build curated agent skills for coding CLIs, terminal tools, context engines, remote bridges, and multi-agent runtimes
-
neatcontext-plugins
Turn long AI conversations into reusable domain knowledge across sessions
-
@ccsk/cli
Claude Code Starter Kit CLI — scaffold Claude-ready projects in one command
-
leerness
Leerness: 비파괴 마이그레이션, 자동 버전 감지·업데이트, 계획/진행/핸드오프 자동화, 게으름·시크릿·인코딩 자동 가드, Claude Code 슬래시 통합을 갖춘 한국어 우선 AI 개발 하네스.
-
@oomkapwn/enquire-mcp
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
-
openclaw-memory-kit
Provide AI agents on OpenClaw with a full memory system for context saving, auto backups, file management, and session recovery.
-
harness-engineering
Provide tools and best practices for building and running long-running AI coding agent harnesses with Claude Code integration.
-
devlyn-cli
AI development toolkit for Claude Code — ideate, auto-resolve, and ship with context engineering and agent orchestration
-
themoltnet
Accountable authority for autonomous agents
-
d-nd-seed
Portable operating substrate for AI coding agents: runtime memory, hooks, guardrails, continuity, capability routing and governed self-improvement.
-
aria-knowledge
Applied reasoning, persistent agent memory, context engineering, and human-governed trust for AI coding agents — Claude Code, Claude Cowork, Codex, Cursor, Antigravity. Compatible with Obsidian.
-
diffctx
Smart git diff context for LLMs and AI agents — selects the minimal code fragments needed to understand a change, under a token budget. Deterministic, local, MCP server included. Also exports a full codebase to YAML/JSON/MD.
-
fest
Template Driven Agent Orchestration
-
Kote
A developer memory layer that automatically captures and organizes AI sessions, Git history, and development context into searchable knowledge.
-
engrene-memory-bridge
Bridge AI tool memory with local files for shared context, resume work across IDEs and CLIs, and avoid vendor lock-in
-
Work_Review
Track and organize your work activity automatically, creating clear records of app use, websites visited, and screen content for easy review and reporting.
-
RightMemory
Tree + graph memory for AI coding agents, backed by Git-syncable Markdown.
-
ultra-builder-pro-cli
Multi-runtime installer for the Ultra Builder Pro agent-engineering system — deploys commands, agents, skills, and hooks to Claude Code, OpenCode, Codex CLI, and Gemini CLI.
-
rtfm
The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 22 parsers (incl. EPUB, DOCX, ODT), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.