context management

Leviath is a Rust-based agent runtime for running structured LLM agents from a single file. It emphasizes context regions, stage-specific models and tools, run journaling, live steering, and the ability to run many agents in one process.

A terminal-based AI coding agent written in Go. It supports multiple model providers, minimal built-in tools, skills, MCP, subagents, session resume, and compact context handling for software development workflows.

A TypeScript library for deterministic context folding in long-running LLM agent sessions, designed to preserve prompts, avoid extra summarization calls, and keep provider caches hot.

Open-source context layer for data and analytics agents that adds warehouse context, semantic search, and MCP/CLI access for tools like Claude Code and Codex.

CoreMem is a context management platform for AI agents and chat tools. It lets users store preferences and notes as reusable mems, then load them into tools through MCP, public profile URLs, scoped share links, and AI-readable docs.

Self-hostable MCP server that collects memories from coding agents and regenerates shared AGENTS.md-style context for the next session.

Shared AI-context platform for teams that captures decisions, gotchas, and domain knowledge once and makes it available to agents through MCP and popular coding/chat tools.

Meetless is a control layer for AI coding agents that captures decisions from live coding sessions, flags stale or conflicting instructions, and injects approved context before the agent acts. It’s built for solo developers and teams using Claude Code and Codex.

Rudi is a Python tool for LLM memory management that replaces a growing chat transcript with a causal dependency graph, aiming to keep token usage flat across long sessions. The README shows benchmarking results, fold behavior, and example usage with get_slice, store_decisions, and run_turn.

An experimental RAG lab for constrained environments, with configurable document classification, chunking, retrieval, reranking, and chat context assembly. It includes Open WebUI integration and emphasizes debugging retrieval and context failures.

A local-first, file-based context and memory system for AI coding assistants. It’s designed to persist decisions, tasks, and learnings across sessions so tools can rehydrate project context instead of starting from scratch.

Local-first task and context manager for humans and AI coding agents. It stores tasks, plans, docs, and memory in a shared SQLite database, with CLI commands, a web UI, and agent attribution built in.

Open-source Claude Code plugin and skill for saving a compact handoff before hitting rate, usage, or context limits, then resuming in a new session without replaying the full transcript.

An open-source protocol ecosystem for controlling LLM behavior during software development, with a focus on preventing context drift and code regressions through minimal diffs, inspection-first workflows, and snapshot-based session handoff.

A technical case study on reducing token usage in a coding agent, including a model-free harness, wire-level measurement, and several concrete optimizations that cut a long run from 1.04M to 517k tokens.

Open-source AI agent harness tool that lets an agent wipe its session context and replay the first message, designed for loop-based agent workflows.