Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 25 of 41

MUMA-Mem★ 3

Multi-user multi-agent memory system for OpenClaw. Replaces the default file-backed memory with an intelligent, layered architecture featuring ACT-R activation scoring, Ebbinghaus forgetting curves, Zettelkasten-style note linking, and automatic consolidation.

scratchpad★ 3

One shared Markdown file that AI agents take turns writing to — context, decisions and progress all live in the file, so any agent can pick up the work without you summarising the last chat. Single binary: CLI + MCP server + live Web UI

LifeMem★ 3

Official implementation of LifeMem: longitudinal memory for more faithful, diverse, and dynamically evolving LLM agents.

Noetica-agent-lab★ 3

Research-oriented cognitive AI architecture exploring memory, reasoning, planning, and adaptive learning using local LLMs.

shiroe★ 3

Local-first AI project memory and control runtime for evidence, privacy, model routing, human approvals and cross-harness handoffs.

AgentMemoryService★ 3

Web API sample with Microsoft Agent Framework, Azure OpenAI, and SQL Server that adds persistent per-user memory to AI agents through authenticated chat endpoints and automatic memory extraction.

agent★ 3

Previously on you. A self-evolving AI agent that remembers by when, not by chat thread — it learns who you are, out in the open. Memory as plain Markdown in your own repo.

Anona-Memory-SDK★ 3

Official Python and TypeScript SDKs for Anona Memory managed memory for AI agents. Record, retrieve and reason over memories, with framework adapters and an MCP server.

nevertwice★ 3

Local-first memory for AI coding agents that catches a mistake before it repeats. Plain Markdown + git, zero deps, every agent via MCP/hooks. Formerly Anamnesis.

openclaw-self-evolving★ 3

Analyze OpenClaw session logs to generate weekly self-improvement suggestions for AI agents without silent modifications.

EvidenceSpine★ 3

Agent-agnostic evidence-bound memory and handoff side-car for multi-agent systems. Claims carry checksummed excerpts — verified means re-verifiable, stale evidence gets flagged. MCP server, CLI, and git hooks. Apache-2.0.

agentic-context-engineering★ 3

ACE — Agentic Context Engineering: evolving, self-improving context playbooks for LLM agents. Faithful ICLR 2026 implementation with OpenAI Agents SDK support.

recall★ 3

An intelligent memory gateway for AI applications that automatically extracts, manages, and retrieves relevant long-term context without bloating the model's context window.

Kairo★ 3

Persistent engineering memory & session-continuity control layer for AI coding agents (Claude Code, Codex, Cursor, Gemini), built on the Model Context Protocol. Scans a repo once, remembers architecture/decisions/changes, checkpoints safely, and hands the next agent an exact continuation brief — so agents stop rescanning and losing context.

hebbian-mark-graph★ 3

Lightweight long-term memory retrieval for chat agents using NPMI + Hebbian learning — no vector database or embedding model required.

context-router-lab★ 3

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

mem0-temporal-hygiene★ 3

Temporal context, CRUD tools, and automated deduplication for Mem0 OSS + Qdrant. Fixes time-blindness and conflict resolution gaps.

DBX-Database-Extreme★ 3

DBX is an open-source, high-density in-memory database engine built in Go, engineered specifically to serve as the secure memory layer for multi-tenant AI agents. Unlike general-purpose databases that rely on logical access controls, DBX enforces **per-tenant physical isolation** at the kernel level. By leveraging Linux Landlock and `SO_PEERCRED`

Contextra★ 3

Contextra is a high performance AI context engineering platform built in Rust for document ingestion, retrieval, embeddings, memory, prompt orchestration, and multi-LLM application development.

openrook★ 3

Open-source runtime for LLM agents with persistent memory, relationship history, modeled mood, and evolving identity. Carries state across conversations into prompts for Ollama, OpenAI-compatible backends, or Codex. Inspectable state, with opt-in autonomous research mode.

TokenWorth★ 3

Official implementation of Learning What to Remember: Resource-Efficient Self-Improvement for Lifelong Agents. TokenWorth learns memory worth from execution feedback.

graph-mempalace-plugin★ 3

Claude Code plugin: a knowledge base of your project's conversations and code that builds and updates itself (MemPalace + Graphify)

CONTINUUM★ 3

AI Work Continuity & Cross-Model Agent Handoff System. Captures, verifies, and packages deterministic project state across Claude, GPT-4o, Gemini, Cursor, Antigravity & Local LLMs.

deepshrink★ 3

Proven-freshness context store for coding agents - mtime-verified reuse, TF-IDF recall, faithful compression. 100% local, 0 dependencies.

Awesome-LLM-Agent-Experience-Lifecycle★ 3

The Experience Lifecycle of lifelong, self-evolving & memory-augmented LLM agents — acquisition, representation, retrieval, consolidation, abstraction, internalization, revision, distribution + governance. Companion to the survey.

ExpHarness★ 3

[arXiv] ExpHarness: Model-Agnostic Experience Learning through a Trainable Harness

penpal★ 3

Penpal MCP: a local-first memory layer for AI agents on macOS. Gives Claude Code, Codex and Cursor searchable, cited memory of your browsing, clipboard, windows and past AI sessions, with per-agent grants and redaction. No cloud, no built-in LLM.

memoria-nox★ 3

Self-hosted memory for LLM agents - one SQLite file, zero services, MIT. Hybrid retrieval (FTS5 + sqlite-vec + RRF) with pain-weighted salience and a knowledge graph. Under matched embeddings, outperforms Mem0 on LoCoMo and LongMemEval. Your data, your provider, your disk.

vayl★ 3

Memory for AI agents where a wrong fact causes harm. When a medication or an account status changes, Vayl retires the old value, keeps the history, and double-checks risky changes before they apply. Open source, local-first, works with any MCP client or agent framework.

actrone-memory-py★ 3

Persistent memory for AI agents in Python. Short-term session memory plus long-term semantic recall, local-first with no services to run, and Redis and Qdrant when you scale. Adapters for LangChain, LangGraph, CrewAI, LlamaIndex and 12 more frameworks.

semantic-layers★ 3

Install and connect formally verified and executable concepts and rules.

SwitchMem★ 3

Adaptive memory modality selection for GUI agents: learning when to use text or image memory at each interaction step.

memk★ 3

A dependency-free memory kernel for agents: claims with authority, freshness and verifiable provenance. SQLite and the standard library only.

somna★ 3

Nightly memory curation for Claude Code on your Mac. Injects repo and client context at session start and keeps it current while you sleep.

codex★ 3

Memory for AI agents: beliefs with a source, a certainty and a revision history. SQLite, zero deps, MCP server.

common-context-mcp★ 3

common context MCP — shared, append-only context store for AI agents over MCP: checkpoints, failures, file claims, handoffs and crash recovery. npm: https://www.npmjs.com/package/common-context-mcp

llm-sieve★ 3

Transparent context reduction for LLMs. A proxy between your agent and your LLM endpoint.

epoptes★ 3

Long agent runs. Under watch.

mempabench★ 3

MemPABench: an interactive benchmark for on-policy evaluation of personal-agent memory for interaction preferences

RELAY-2★ 2

context handover with increased security, brain child of RELAY_context

hydra★ 2

The AI that remembers you. Forever. — A living digital entity built in Rust. 68 crates. Self-writing genome. Persistent memory. Constitutional governance. Drop a TOML file, Hydra learns.

memo-brain★ 2

Long-term memory for AI coding assistants. Rust CLI with semantic search, Agent Skill integration, and local deployment.

Sacred-Essence-Viking★ 2

Markdown-first, local-first memory architecture for AI agents with lifecycle, distillation, and human-readable memory artifacts.

anticipation-layer★ 2

Persistent Anticipation Layer for LLM Agents — Pre-compute possible futures during idle time for faster, cheaper and more proactive decisions. Bio-inspired temporal awareness (short/medium/long-term horizons).

ctxbudgeter★ 2

Context compiler for agentic AI — token budgets, cache-aware adapters, pytest-style eval layer, JIT references. Framework-agnostic, local-first, deterministic

firm-ecosystem★ 2

Architecture documentation for the Firm AI Agent ecosystem — setup-vs-agent-firm + mcp-openclaw-extensions + Memory-os-ai

context-engineering★ 2

Context engineering toolkit for LLMs — pack, cache, debug, red-team, and orchestrate context windows. Council of Experts, adversarial testing, immune system, context compiler, drift detection, multi-agent entanglement. TypeScript + Python.

magi★ 2

MAGI — Multi-Agent Graph Intelligence. Universal memory server for AI agents. MCP + gRPC + REST API with semantic search, knowledge graph, and behavioral pattern analysis.

ecodb★ 2

Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 22+ MCP tools.

mimic★ 2

Cognitive infrastructure for AI agents

openclaw-shared-memory-manager★ 2

Privacy-first shared-memory governance skill for OpenClaw teams, with safe canonical notes for groups, projects, and dispatcher-led delegation.

memocean★ 2

MemOcean — A shared knowledge base system for Chinese multi-agent scenarios. Fork of MemPalace.

multi-agent-memory-skill★ 2

Hermes Agent 多智能体记忆管理 Skill — 惰性索引、Context注入、记忆回收、主权管理(方案B实现)

MindVault★ 2

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

emu★ 2

Stop burning API tokens. 9 algorithmic engines for real-time context optimization, infinite-loop detection, and smart prompt compression.

lago★ 2

Event-sourced persistence for AI agents — append-only journal, SHA-256 blob store, knowledge graph, memory API. Part of the Life Agent OS.

agent-agentic-context-engineering★ 2

⚖️Agentic Context Engineering (https://arxiv.org/abs/2510.04618) implementation using Agent Framework

Cortex★ 2

Cortex System: The Operating System for AI Engineering. Cure Technical Amnesia.

Cerebro★ 2

The open-source memory engine behind Cerebro. Persistent memory, learning and reasoning for Claude Code and any MCP client. Local-first.

Stratum★ 2

The self-optimization layer for AI agents.

lethe★ 2

Local graph-based memory for agents. Memories reinforce when used and fade when ignored.

KBase★ 2

Agentic Knowledge Base Framework — self-organizing knowledge for AI agents

errloom★ 2

Errloom: the context engineering framework for shoggoth whisperers; weave beautiful agentic RL tapestries using the Holoware DSL.

purmemo-mcp★ 2

MCP server for pūrmemo — AI conversation memory that works everywhere. Save and recall conversations across Claude Desktop, Cursor, and other MCP-compatible platforms.

UlisseMemo★ 2

Personal AI with persistent memory. Turns any LLM into an entity that remembers who you are, learns from your conversations, and grows over time. Local, private, yours.

seiryu★ 2

青龍 Seiryu — AI 記憶與傳承模組。讓 AI 的記憶不再隨視窗關閉而消失。基於 LDRIT(生死遞迴智能理論)設計。

oniondb★ 2

A geometric memory database with importance-stratified shells, HNSW acceleration, and mass-weighted decay scoring. Zero to hero: SQLite → 10M+ records.

primkit★ 2

CLI-native state persistence for AI agents — tasks, memory, state, and queues. One binary per primitive. No setup. No infrastructure.

mneo★ 2

Persistent memory for AI agents using git refs. MCP server + Claude Code skill. No vector database, no embeddings, no daemon — branches are scopes, push/fetch is sync.

Mimir★ 2

Experimental pre-1.0 multi-agent memory governance/control plane

vibe-brain★ 2

🧠 Persistent project memory for AI coding agents. Your agent never forgets, never drifts, never re-asks. Works with Claude, Cursor, Windsurf & more.

TraceCC★ 2

TraceCC gives AI agents a CLI-native long-term memory over their own session history. Searchable, scoped, and sized for context windows.

ContextDrone★ 2

Build the context from anywhere, then bring it to any AI.

Engram★ 2

Δ Engram is a deterministic reasoning kernel — symbolic AI, a finite state machine, with configurable boundaries and self-improving weights

mnemebrain-rust★ 2

Rust SDK for MnemeBrain — a belief memory system for AI agents. Supports MnemeBrain Lite and Full APIs.

Mnemos★ 2

Persistent local MCP/CLI memory system for AI agents. CPU-only, 98.94–99.15% R@5 on LongMemEval. Named after Mnemosyne (Greek: μνήμη, memory).

asof★ 2

Temporal-awareness hook for tool-using LLMs — surfaces freshness verdicts on in-context data so stale information doesn't poison fresh reasoning. Adapters for Claude Code, Antigravity, and any generic harness.

signal-api★ 2

Persistent memory for AI agents. Two lines of code. Works with LangChain, CrewAI, AutoGen, Claude, MCP. Free tier. Self-hostable. MIT.

colony★ 2

Polymathera's no-RAG, multi-agent framework for extremely long, dense contexts (1B+ tokens).

do-agents-leave-footprints★ 2

Do agents leave footprints? A system for deliberate orientation when minds enter long-lived territories.

cycgraph★ 2

Agent context compressor and memory persistent orchestration

aether-os★ 2

One assistant. Many vaults. No bleed. — a free, MIT personal-AI scaffold on Claude Code with governed memory + an IP-clean filter.

nexus-mind★ 2

🧠 Nexus Mind - Where Intelligence Connects | 三引擎智能记忆系统 | 孕育智慧 · 启迪创新

context-bridge★ 2

Persistent memory and replanning for Claude Code. Checkpoints what Claude was doing and injects context at the start of the next session.

ai-chief-of-staff-engine★ 2

A working, tested memory engine for an AI chief of staff: a SQLite fact store with full write history, session commands, enforcement hooks, incident logbook, self-tending rituals, capability registry, mode contracts, and 12-week cycles. Eight staged releases with probes and CI.

contextos★ 2

Persistent engineering context for AI coding agents. MCP server with auto-hydration on session start.

context-continuum★ 2

Fight AI context rot: keep Claude Code (and any LLM) sharp in long sessions with one living Checklist instead of lossy /compact summaries. Persistent working memory + context-window HUD + zero-keystroke auto-clear.

context-compiler★ 2

Deterministic state engine for managing conversation state and constraints in LLM applications.

AI_Chatbot_with_Memory★ 2

gradio region:us

llm-memory-requirement★ 2

streamlit region:us

Agentic-Context-Engine★ 2

static region:us

worldwave-agent★ 2

A persistent cognitive entity — one agent, one memory, one timeline across all platforms. Self-editing knowledge graph, cross-platform identity, P2P network.

GhostKG★ 2

Dynamic Knowledge Graphs with Memory Decay for LLM Agents

shared-memory★ 2

Portable semantic memory layer for LLM agents over MCP

agent-memory-kit★ 2

Local-first, layered memory kit for AI agents — stdlib-only, zero deps

crucible★ 2

Multi-agent collaboration engine with persistent, searchable, self-compacting memory. Agents research, critique and adjudicate over a shared SQLite memory with hybrid BM25 + embedding recall. Zero-dependency core, runs locally on Ollama.

hypercube★ 2

Context Transform Engine.

sqlite-graph-memory★ 2

Graph RAG on SQLite for AI agents: vector retrieval + hand-curated wikilink graph + cross-encoder rerank, with a zero-token per-turn memory ledger. Working pilot.

havamal★ 2

Judgment continuity for AI agents — load your project's scars, taste, and non-negotiables into every session. Judgment-layer companion to edda. (formerly project-doctrine)

vayl★ 2

The reconciling memory layer for AI agents (MCP server): a new value supersedes the old, "we dropped X" actually retracts X, and history stays queryable — so agents get current facts, not stale ones.

More in Agent frameworks & infrastructure