#context-engineering

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.

🔁 Build reliable recurring AI-agent systems: 1025 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Stop your coding agent reading the wrong files. Compiler-grade TS/JS repo map — 100% precision on blast radius vs grep's 60%, measured on public repos. CLI + MCP server, fully local, no vector DB.

Perseus Context Engine — resolve verified workspace state before the context window opens. Local-first, MCP-native, MIT.

The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.

The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.

Self-hosted AI coding agent platform for GitLab, built with LangGraph. Reviews merge requests, resolves issues autonomously, and chats with full project context.

Claude Code memory system — auto context injection, drift detection, compounding, FTS5/vector search, Obsidian vault export. Zero core deps.

Gobstopper makes long Claude Code and Codex sessions smaller. A local proxy compacts live requests, and saved sessions get a smaller copy beside the original.

Logic programming for AI agents: Datalog-family language compiling to optimized SQL

AILmanac — the always-current, community almanac for getting the most out of Claude and every AI. For all levels.

Universal Context, Rules & Handoff Bridge for AI Coding Tools (Cursor, Copilot, Cline, Claude Code, Antigravity, MCP)

git diff for your agent's context window. See exactly what your LLM saw — turn by turn, block by block.

An interactive roadmap for harness engineering — building the agent loop, tool layers, context engineering, memory, retrieval, eval harnesses, and the rest of the scaffolding around modern LLMs.

See what your AI coding agent silently drops from its instruction files. A byte-exact truncation X-ray for AGENTS.md / CLAUDE.md / .cursorrules.

Local-first AI agent platform with a Tauri desktop app and Rust CLI. Run governed tools, durable sessions, multi-agent workflows, modular packages, and one-shot effect permits.

Reusable Interpretable Context Methodology (ICM) workspace template for filesystem-based AI agent workflows

One-command agentic workflow kit for AI coding agents: wires Claude Code, OpenCode, Codex, Cursor, Gemini CLI, Oh My Pi and DeepSeek Harness with a 25-agent squad, parallel wave planning, persistent memory and an MCP server. Zero dependencies.

Local memory, context, and trust-boundary layer for cloud LLM coding agents

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.

A self-improving agent-context framework for DeepSeek Harness

One markdown file. Two hooks. Memory that survives Claude Code's context compaction. Zero deps.

Run Claude Code as a teammate that owns work end to end. A maintained CLAUDE.md (works as AGENTS.md) plus a plan/execute/review skill pipeline with external verification, adversarial review, and structurally safe parallel execution. Dated changelog, updated when model behaviour changes.

Technical product management case study for a governed AI context layer, covering architecture, validation, privacy controls, and reliable publishing.

A Claude Code marketplace plugin that inspects a blank folder or an existing repo, interviews what cannot be inferred, and installs a project-specific agent harness: context budget, work graphs, capability tiers, and an agent session runtime.

Best AI Code Architect 2026: Diagram-First Agent Orchestrator with AST Editing & Atomic Commits

Transfer coding sessions between Codex CLI and Claude Code without losing context.

Plan Build Run 2026: Ultimate Claude Code Plugin for Structured Agent Development

Agent context gate for Codex, Claude Code, Copilot, MCP, Cursor, Cline, Gemini and Windsurf repos

A Claude Code skill that builds and maintains a personal, file-based semantic layer as you work, and reloads it every session.

COMPASS — Commitment-Preserving, Position-Aware Semantic Substrate for LLM context

Local-first context cleaner for AI agents.

Questions → Research → Spec → Plan → Implement: a phase-gated Claude Code plugin that keeps a coding agent under 40% context by writing one artifact to disk per phase.

Claude Code plugin: one engineering process, skills that take turns, and agents that keep discovery off the main context.

🚀 ODIN Reflector 2026 – Next-Gen Meta-Reflection Engine for Outline-Driven AI Development

Persistent memory for Claude Code — your sessions distilled into a Google OKF knowledge bundle (plain markdown you own, not a database you're locked into) and injected back at the start of every session.

Beginner-friendly, technology-neutral AI coding workflow for Claude Code and OpenAI Codex—greenfield and existing projects.

Best Claude Code Memory Toolkit Alternative 2026 – Smart Markdown Session Manager