Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 24 of 41

dsh-context-rollover★ 4

Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable notes, verbatim recent tail, no summarization

dsh-memory-inject★ 4

给 DeepSeek Harness 的三层记忆:常驻事实 + 会话摘要 + 全文检索。注入不花任何模型调用,写回用你当前选的模型。

mnemon-memory-agent★ 4

Long-term memory for AI agents on Jev. Keep raw records, judge them with a fast System 1 model and answer from under 4k tokens of context.

dsh-context-pilot★ 4

DSH 上下文智能压缩 + 智能思考:每轮注入用量、模型自主决定压缩并自动续跑;可选让模型按任务难度自主调整思考强度档位

awesome-agentic-memory★ 4

🧠 The definitive curated map of memory for LLM agents — frameworks, research papers, benchmarks, taxonomy & deep dives.

bureau★ 4

The self-hosted bureau for AI agents: they get briefed on missions from a durable task queue, file what they learn into a markdown+git brain, and show up for work in a 8-bit Gameboy inspired office.

freshctx★ 4

Pre-action evidence revalidation for AI agents. Detect stale reasoning before agents write, send, update, or delete.

AgentExperience.NET★ 4

Verified-lesson memory for AI agents: records runs, keeps only what your own check passed, and measures with a built-in holdout whether it helps. .NET/MAF, Python, Go, MCP + CLI (aexp).

FixelRecall★ 4

Local-first context compression and exact recovery for Codex CLI and Claude Code CLI on macOS, Linux and Windows.

logos★ 4

Logos is a tool which allows all your ai agents to share the same context and pick up right after one another

dsh-compact★ 4

DeepSeek Harness 的上下文压缩插件:自动与手动压缩、工具结果裁剪、有界溢出恢复。

2nothing★ 4

Open-source field experiment in persistent AI-agent identity, memory, creation, and interaction. Run the reproducible 10-minute protocol.

layer0★ 4

Self-hosted AI memory and RAG layer with local LLM support. Full Rust implementation with vector embeddings, knowledge graph, FTS5, hybrid search, and OpenAI-compatible API.

folklore★ 4

A decentralized cooperative memory & research layer for AI agents — collectively and cooperatively learning and advancing as a community.

Ripples-of-Aion★ 4

岁月涟漪 · Ripples of Aion — A structured memory layer plugin for Cyrene.

astp★ 4

A cognitive persistence protocol for multi-agent AI systems — hash-chained, auditable records of how agent state evolved, with provenance and governance rules in the specification.

LLM-KNOWLEDGE-LIFECYCLE★ 4

The Knowledge Lifecycle of Large Language Models: a unified five-stage framework for how LLMs acquire, store, retrieve, update, and forget knowledge, with the Provenance Vector proposal and the reproducible Lifecycle Desynchronization metric.

four-layer-memory★ 4

Four-layer memory substrate for long-horizon agents: write-gate admission, signed approvals, hash-chained ledger, revocable and portable.

agentconf★ 4

Save and use agent configs via sqlite

omneum★ 4

Text-blind context control plane for AI agents. Select high-utility context under token budgets.

engine★ 4

Open-source long-term, time-aware memory engine for AI agents (MCP + hybrid search + bi-temporal recall)

citadel★ 4

Local-first encrypted memory for AI agents

lumina-reforge-research★ 4

Research into a new method of context management

claude-brain★ 4

🧠 Empower Claude with memory to enhance code debugging and conversation recall, turning ephemeral chats into lasting insights.

bellamem★ 3

Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact.

inception-core-server★ 3

A modular, extensible Rust-based server providing short-term, long-term, and latent memory services, a chat endpoint with a BaseAgent + Sentience DSL, and integration with ChromaDB and LLM services.

remem★ 3

remem provides agents with persistent, reasoned memory that spans across sessions. Whether you're using Claude Code, Codex, Cursor, Copilot, Antigravity CLI, OpenCode and more.

openclaw-memory-local★ 3

🧠 Local memory plugins for OpenClaw — checkpoint injection, Qdrant semantic recall, auto-capture. Your memories stay on your machine.

cortex-python★ 3

CORTEX for Python -- The World's #1 Memory Architecture for AI • Memory that thinks, learns, and dreams • Synthetic cognition infrastructure for Agentic Ai. pip install cortex-ai

GhostVault★ 3

Local memory for the models you already use: hybrid search, encrypted at rest, unlock to work. Only what you send each turn goes out—Claude (MCP), ChatGPT (Actions), same vault.

CxMS★ 3

OpenCxMS Memory System - Persistent memory for AI coding assistants through structured documentation

capy-cortex★ 3

Autonomous memory and learning system for AI coding agents. LLM-powered knowledge extraction, triple fusion retrieval (FTS5 + TF-IDF + entity graph), quality-gated storage, and self-curating consolidation. Your agent never makes the same mistake twice.

xstitch★ 3

Cross-tool memory for AI agents. Stitch context across Cursor, Claude Code, Codex, Gemini CLI, Windsurf, Copilot, and 9+ AI tools. Preserves decisions, failed experiments & warnings across sessions. Zero dependencies, MCP + instruction files, BM25 relevance search. Never re-explain your work.

memoclaw-skill★ 3

Semantic memory API skill for AI agents

headkey-legacy-poc★ 3

Cognitive Ingestion & Belief Formation Engine. Long term AI memory.

TLCM★ 3

Temporal Layered Context Memory (TLCM). The architecture for AI that treats memory as a living timeline instead of a flat filing cabinet.

agent-memory-store★ 3

Lightweight persistent memory for AI agents. SQLite, zero mandatory dependencies, privacy controls (forget/TTL), full audit log. Drop into any agent in 3 lines.

synapse★ 3

🧠 Synapse - Supercharge your AI coding assistants with memory, context, MCP tools, and intelligent routing. Works with Cline, Roo, Cursor, and any OpenAI-compatible tool. Just change the API endpoint and get superpowers! ✨

Long-Term-Memory-Agent★ 3

Build an AI Agent with long term memory using LangGraph

synapse★ 3

The privacy-first memory engine for AI agents. Setup wizard, per-user vaults, smart inbox, natural-language forget, MCP server for Claude/Cursor/Windsurf. Zero API calls. Zero dependencies. Pure Python.

autogen-multi-agent-memory★ 3

AutoGen Multi-agent Conversation and Recall using Memori

ulmen★ 3

The serialization engine for LLM agentic workflows. A drop-in Python/Rust replacement for JSON that mathematically reduces context window bloat by 44% and deserializes 3x faster. Built for multi-agent swarms, RAG memory, and AI orchestration.

MindFox★ 3

Offline NPC memory middleware — 16-byte factor vectors, SQLite only, no cloud. NPCs remember, forget, and dream.

Cortex★ 3

🧠 Universal long-term memory for AI agents. GraphRAG-powered knowledge base with vector search + graph traversal. Privacy-first, local-only, MCP-compatible. Connect Claude, Copilot, or any AI assistant.

MemoquasarEterna★ 3

A toy local memory system for multi-agent workflows

ION★ 3

ION: Context engineering & agent governance

MKEvo-cognitive-runtime★ 3

A cognitive runtime architecture for LLM continuity, memory, identity, and safe pseudo-conscious agents.

Airline-booking-demo-strandsagent-agentcore★ 3

An airline customer service AI agent demo built on AWS Bedrock AgentCore with Strands Framework, featuring Gateway policy enforcement and Memory (STM/LTM). 基于 AWS Bedrock AgentCore 构建的航空客服智能代理演示系统。

recollect★ 3

Recollect is a memory layer for AI agents that provides robust context compaction for long-running chats.

consciousness★ 3

A powerful, pluggable vector memory and Model Context Protocol (MCP) server for local semantic search and long-term memory.

kodama-claude★ 3

Kodama for Claude Code — Reliable session memory & smart restart for the Claude CLI

memory_orchestration★ 3

Layered memory system for LLM agents using semantic, episodic, and procedural memory with Qdrant-backed long-term storage.

cogniweave★ 3

An agent that Knows You, Remembers You, and Understands You

ccmem★ 3

CCMem - Claude Code Memory: Standardized MCP server providing persistent project memory and context-aware development assistance for Claude Code

bookend-skill★ 3

Never lose context again. Structured memory system for Clawdbot/Moltbot. Built by Nox ⚡

fourgods★ 3

AI 助手的模組化能力框架:記憶、防禦、診斷、品質穩定 | Modular capability framework for AI assistants | Claude Code / Cursor / Any LLM

infinite-memory★ 3

Seamless, infinite context for your LLMs. Handles long conversations and long messages.

claude-session-recorder★ 3

Give Claude Code a memory that persists across sessions and survives context compaction. Zero dependencies, pure Python, 30-second install.

claude-memory-lifecycle★ 3

Connection-based memory lifecycle for Claude Code — entries that connect to other knowledge survive, isolated ones fade. Built entirely with hooks.

GroundMemory★ 3

Persistent identity and memory across AI tools - mcp-native, local-first, framework-agnostic, production-ready.

context-engineering-workshop-java★ 3

Hands-on workshop to learn how to implement context engineering with Java, LangChain4J, and Redis

memlane★ 3

Memlane is where you can store you memories that you think you will forget, but it never

LLM_Context_Orchestrator★ 3

CLO (Cross-LLM Orchestrator) is a specialized browser extension designed to eliminate context loss when switching between different LLM platforms. It acts as a **"Reasoning State Virtual Machine"**, capturing the cognitive state of a conversation and enabling it to be "rehydrated" into any other model seamlessly.

hippo★ 3

A Go LLM client with a memory. Every provider, cost-aware, single binary.

openowl★ 3

AI browser memory for anyone who works in a browser. Local-first, private, BYOK.

xstitch★ 3

Enable AI agents to share memory across tools and avoid repeating work when switching between tasks or platforms.

mimir-well★ 3

Mímir's Well — AI memory database with Ebbinghaus decay, self-healing, backup rotation, and full-text search

nur★ 3

A cognitive runtime that gives LLM agents persistent state, identity, and learning across turns. Memory, beliefs, drives, self-evolution, skills, and affective state — engineered scaffolding outside the model.

llm-personality-design-patterns★ 3

Reusable design patterns for long-running LLM agents with stable identity and controlled change.

plurum★ 3

Collective intelligence layer for AI agents — search what others already solved, publish what you learn, never start from zero.

BABYLON-60★ 3

Tamper-evident memory & decision lineage for AI agents. Cryptographic proof of what your agent knew. Powered by a hybrid Python/Rust (Direct-Silicon) core.

multi-agent-graph-memory★ 3

Persistent graph memory architecture for multi-agent AI systems using Graphiti, FalkorDB, and MCP.

eidentic★ 3

Eidentic is the open-source TypeScript SDK for AI agents with self-improving memory and production fundamentals built in.

Memory-os-ai★ 3

Memory OS AI — Adaptive memory system for AI agents (forked from RoaminS/Memory-os-ai)

mycelium★ 3

Simple node based memory system for AI agents. Built in Swift. CLI, MCP (stdio and HTTP), and observation WebSocket server.

claw-migrate★ 3

Memory migration tool for the Claw AI agent ecosystem — WorkBuddy, OpenClaw, QClaw, CoPaw and more

mem9★ 3

Enable AI agents to retain memory across sessions using persistent storage designed for continuous context retention.

BrainRouter★ 3

BrainRouter is a cognitive memory and multi-agent orchestration platform for AI coding agents. It provides a first-party terminal CLI, MCP-based memory tools, layered recall, context compaction, graph memory, and dashboard inspection workflows to help agents preserve long-running task continuity while reducing prompt size and inference cost.

icemage★ 3

Token-efficient context engine for AI coding agents. v2.23.0: token-killer pack - deep-forget (unlearning propagation), dangling-reference guard, MCP schemas-on-demand. 2694 tests, 43 MCP tools, Elastic-2.0.

Cairn★ 3

Cairn (AI agent recovery library) v1.0.0: a framework-agnostic Python library and benchmark that lets long-horizon AI agents recover from crashes by re-grounding, not replay.

engram★ 3

MCP memory server for Claude Code, Cursor and AI agents - Rust local-first AI memory with hybrid search, SQLite, knowledge graph and Python/TypeScript SDKs

context-compression★ 3

Reduce token usage for JSON, CSV, and TSV files with deterministic compression that keeps data intact for AI agents.

buddy★ 3

The open-source memory for AI agents — it gets smarter the more it remembers, not slower or costlier, and never confidently remembers wrong. Plain files, no database, bring your own model. Works with Claude Code.

graphifychat★ 3

Turn any conversation into a portable knowledge graph. TRON + Sparse6 + psychology — paste into any AI.

another-brain★ 3

Long-term memory your AI coding agents actually share. One brain, many agents — standalone embedded MCP server: SQLite + FTS5 + vector hybrid search, local ONNX embeddings, self-expiring diary. No server, container, or daemon.

memora★ 3

Reference implementation of the Bitemporal Provenance Memory Architecture (BPMA): an append-only, bitemporal, provenance-first memory ledger for AI agents.

Amber★ 3

A knowledge management platform which acts as a persistent, structured, and token-efficient memory layer for large language models

claude-teams-brain★ 3

Reduce token use and enable persistent memory for Claude Code, boosting efficiency in solo or team agent setups.

hermes-headroom-plugin★ 3

ARCHIVED — historical Hermes/Headroom integration experiment; use the upstream retrieval-only plugin as baseline.

llm-tool-history★ 3

Lazy-loaded context management for LLM external calls. Archive tool/skill/MCP results after each turn, replace with compact stubs, and give the model a query tool to retrieve past results on demand. Context stays lean — nothing is lost.

hermes-cmx★ 3

Context Memory eXchange — a retrieval-first, engine-enforced-grounding context engine for Hermes Agent and a drop-in LCM replacement. Keeps 100% verbatim history (SQLite FTS5+trigram+embeddings; Postgres optional), retrieves exact slices every turn, and forces + verifies grounding so the model answers from real history or honestly refuses.

clear★ 3

Context Layering & Engineering for Agentic Resources — Persistent memory, intelligent context, and structured project management for Claude Code

tooltrim★ 3

Drop-in compression for LLM agent tool outputs: cut ~99% of tool-result tokens while keeping (often improving) answer accuracy. Provider-agnostic, with a faithfulness benchmark and an OpenAI-compatible proxy.

build-your-users-mind★ 3

A recipe for any AI agent to build a self-improving theory-of-mind model of its user from interaction logs (feedback precognition). What you mind is what you get.

utopia-os★ 3

An open framework for a persistent, self-regulating AI operations system on a coding-agent CLI: tiered memory + SSOT, security-first gates, a knowledge pipeline, multi-agent protocols, session survival, and a zero-dependency cockpit.

HyperAI★ 3

A production-style AI assistant with real-time streaming, semantic memory (STM + LTM), and contextual conversations powered by Gemini, Pinecone, and Socket.IO.

thimiko★ 3

Chat history search for your llm

llm-tool-history★ 3

Lazy-loaded context management for LLM external calls. Archive tool/skill/MCP results after each turn, replace with compact stubs, and give the model a query tool to retrieve past results on demand. Context stays lean — nothing is lost.

agora★ 3

Autonomous research org shipping measured, reproducible results on AI agent memory & reasoning — a public replication ledger (the Crucible), the RAMR benchmark, and mnemo, a zero-dependency memory core. Every claim ships with runnable code that could prove it wrong.

agent-wiki★ 3

Agent-first protocols for LLM memory, active workspace, skill lifecycle, councils, and stewardship—with explicit maturity, evidence, and conformance.

More in Agent frameworks & infrastructure