#context-management

The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, and OpenCode. Zero cloud lock-in.

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already hold, learns what is missing, and leaves every solved path behind for the next goal. Nothing is called done until a check passes.

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.

Preserves a long-lived repository's engineering context — an architecture index, an impact map, session records, and the decisions behind them — as markdown committed beside the code, so an agent reads instead of rediscovering. Repository-local, no network, Python stdlib, MIT.

Async hierarchical memory middleware for LLM agents.

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

Enhanced fork of OpenWolf — a token-conscious second brain for Claude Code, with bounded storage, self-maintenance (openwolf doctor), .wolfignore scoping, and tunable retention. AGPL-3.0.

Controlled coding-agent harness ablations with auditable traces, reproducible evidence bundles, and SWE-bench interoperability.

Local memory across Claude Code, Codex (CLI & Desktop) and more. Reads your transcripts, serves context via MCP.

Relation-aware, calibrated and provenance-preserving context routing for interleaved agent conversations

Swift agent runtime for Apple platforms. Keeps tools, skills and history inside the 4,096-token on-device window, so connecting an MCP server doesn't break the turn. FoundationModels / MLX / OpenAI / Anthropic / Gemini.

A markdown-based memory system for AI agents — stop re-explaining and re-debugging across sessions and models.

OpenCode memory governance plugin — Knowledge Graph + Hybrid Search + Smart Compaction + Tool Firewall + Stop Gate. 6 MCP tools with slash-command UX. Apache-2.0.

Project Intelligence Platform for AI Coding Agents. Scan, audit, generate, and monitor context files (CLAUDE.md, AGENTS.md, CURSOR.md, GEMINI.md) for 6 AI agents. Auto-detect drift, one-click fix, CI integration, MCP server.

Verbatim recall across Claude Code sessions, plus a gate against oversized skills. Pure Node, no dependencies, nothing leaves your machine.

Session continuity for Claude Code: deterministic pre-compaction capture,verified handoffs, post-compaction re-anchoring

Claude reads the part of a large file that answers your question, not the whole file. A PreToolUse hook. Measured: -36% cost on the reads it fires on, no answer lost.

OpenAI-compatible context gateway & proxy for local LLMs (LM Studio, Ollama, etc.). Enforces strict token budgets, deterministic archival, and safe tool-calling for AI agents.

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

Obsidian-based persistent memory framework for AI coding agents. Set it up with just a single prompt.

Cross-session, cross-machine context handoffs for Claude Code. /handoff distills a session into a git-syncable HANDOFF.md; /catchup resumes it anywhere.

Reference architecture for long-running AI coding agents: Compression / Health / Checkpoint / Recovery. Composes pxpipe, session-health, and compact-plus for Claude Code, with a Codex AGENTS.md adapter.

Context-engineered terminal LLM assistant — streaming, multi-turn memory, automatic context summarization, token tracking.

Session close for Claude Code that writes to native memory. /close distils the session into long-term memory; /close-new-session adds a chained handoff file and a ready-to-paste resume prompt.

Claude Code's persistent memory system (CLAUDE.md & project-slug MEMORY.md) for OpenCode.

Share project context across ChatGPT, Claude, Cursor and other AI assistants using portable Markdown files and GitHub

File-based memory governance for AI coding agents (Claude Code, Codex, etc.)

AI Context Window Saver 2026 - Auto Save & Resume Workflow for Developers

Passphrase-based, LLM-agnostic session handoff for Claude Code, Codex, Gemini CLI, Antigravity, and any AGENTS.md-aware tool.

Automatic session handoff for coding agents — never hit a context limit again. Claude Code & Codex CLI.

Local-first Agent Skill for durable, bounded project context.

CLI that scans any repo and scaffolds a .workspace/ dir with context and a Claude Code adapter

Measure Claude Code token use, cut the waste, and prove your savings with a real before and after. Local, private, measured from your own usage counters.

MCP server that gives AI coding agents persistent memory of your codebase: notes pinned to files, spans, and symbols that survive refactors. Works with Claude Code, Cursor, and any MCP host.

Controlled coding-agent harness ablations with auditable traces, reproducible evidence bundles, and SWE-bench interoperability.

Provider-neutral audited Agent Skills with search-first loading, exact bundle identity, and traceable research packets.

Model-driven context folding for the Pi coding agent — the model folds its own conversation into summaries it writes, and the originals stay on disk

Claude Code hooks that measure live context, warn as it grows, and force a detailed handoff note before a long chat gets expensive.

Claude Code plugin: hand off to a fresh session at the end of a task instead of compacting mid-work. Asks after /clear whether to pick it up.