SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Python agent-memory Projects
-
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
Project mention: Use ai-agent-book as a Lab Manual, Not a 12,000-Star Reading List | dev.to | 2026-07-21
The open-source repository bojieli/ai-agent-book contains the Chinese book Understanding AI Agents: Design Principles and Engineering Practice, a compiled PDF, and chapter-based code. It uses the Apache-2.0 license.
-
cognee
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
git clone https://github.com/topoteretes/cognee-integrations.git mkdir -p ~/.hermes/plugins/cognee cp -R cognee-integrations/integrations/hermes-agent/. ~/.hermes/plugins/cognee/
-
Memori
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
-
Project mention: MemU – Personal Memory Shared by Codex, Claude Code, and Hermes | news.ycombinator.com | 2026-07-27
-
Project mention: Dissecting Semantica’s Graph-Native Core: The Missing Layer Between Context and Accountability | dev.to | 2026-09-04
git clone https://github.com/semantica-agi/semantica.git cd semantica python3 -m venv .venv . .venv/bin/activate python -m pip install --upgrade pip python -m pip install -e .
-
Pinned Honcho source tree
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
Project mention: We audited LoCoMo: 6.4% of the answer key is wrong and the judge accepts up to 63% of intentionally | dev.to | 2026-04-04
There is also no standardized evaluation pipeline. Each system uses its own ingestion method (arguably necessary given architectural differences), its own answer generation prompt, and sometimes entirely different models. Scores are then compared in tables as if they share a common methodology. Multiple independent researchers have documented inability to reproduce published results (EverMemOS #73, Mem0 #3944, Zep scoring discrepancy).
-
memsearch
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
MemSearch
-
-
iai-personal-memory-engine
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
Project mention: 50K-token context reloads, replaced by a 2K local memory engine | news.ycombinator.com | 2026-06-28 -
awesome-harness-engineering
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
Project mention: I Was Calling It 'Setup' for Six Months. arXiv Has a Better Word: Harness | dev.to | 2026-05-12When I first skimmed the paper, my reaction was "okay, they invented a word for the thing." A skeptic could fairly say this is academia's contribution to a problem industry already solved. Anthropic ships harness-design blog posts, the awesome-harness-engineering repo lists 80+ tools, and Aakash Gupta's widely-shared post declared 2026 "the year of the harness." Vocabulary alone isn't a contribution.
-
Project mention: Create Context Graph: AI agents with graph based memory, scaffolded in seconds | news.ycombinator.com | 2026-03-24
-
Awesome-Agent-Memory
Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.
Project mention: Listed in Awesome-Agent-Memory: what the maintainer audited, and what the listing actually pays | dev.to | 2026-10-03Yesterday alethech — our verifiable agent memory protocol — landed in TeleAI-UAGI/Awesome-Agent-Memory as the last entry of the Emerging projects block, via PR #136. The list has 657 stars today. The PR was five lines of README. The maintainer closed it unmerged — and landed it by hand with co-authorship credit, as ec176c9.
-
Project mention: Graph RAG finds what's similar. We should aim for what's relevant | news.ycombinator.com | 2026-04-18
-
activity-frames
Turn your workday into structured workflows agents can execute. 100% local, served over MCP.
Project mention: A compiler that turns a day at my computer into agent memory, no LLM | news.ycombinator.com | 2026-08-11 -
memtrace-public
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
That is super cool. Checkout this repo which might give you super power to code quality and cut down 80% of token cost while keeping fable running longer jobs. https://github.com/syncable-dev/memtrace-public?tab=readme-o...
-
PRO-LONG
Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)
Project mention: How a Strands agent took Claude Opus 5 from 30% to 99.95% on ARC-AGI-3 | dev.to | 2026-08-28The specific tools the agent was given didn't come from nowhere. The approach was based on PRO-LONG, which tested how well an agent using GPT-5.5 performed on ARC-AGI-3 as it was progressively given more ways to work with its interaction history.
-
Statewave
Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.
We build Statewave, an open-source memory runtime, so treat the entry about us accordingly. Everything below is Apache-2.0, MIT, or the PostgreSQL License, verified from the LICENSE file rather than the badge, checked on 1 September 2026. MCP is mid-transition from MIT to Apache-2.0.
-
piia-engram
Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.
I packed this into piia-engram — a local-first, content-blind memory layer for MCP clients (Claude Code, Cursor, Codex). Open source, pip install piia-engram. It's local-first mostly because the cleanest answer to "is my memory private?" is "nothing left your machine in the first place."
-
Check out the walkthroughs here for examples of how to learn with Claude Code in Lite mode.
-
deepmem
Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code changes. Self-host for free.
Project mention: Show HN: DeepMem·hybrid-retrieval memory for AI Agents – Vector+BM25+Time-Decay | news.ycombinator.com | 2026-09-08 -
Project mention: Show HN: OpenIndex – Organising domain knowledge into structured data for agents | news.ycombinator.com | 2026-08-20
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
Python agent-memory discussion
Python agent-memory related posts
-
Show HN: IHMT – Infinite Hierarchical Memory Tree for AI Agents
-
memgovern 0.5.0: a `memgovern audit` CLI that shows who your agent's memory trusts
-
Long-term memory for AI coding agents as a tree of plain files
-
Show HN: Open-bridge, how our four-person team works with coding agents
-
Listed in Awesome-Agent-Memory: what the maintainer audited, and what the listing actually pays
-
Three months of running a consultancy out of a git repo our coding agents read
-
Show HN: Memanto.ai
-
A note from our sponsor - SaaSHub
www.saashub.com | 12 Oct 2026
Index
What are some of the best open-source agent-memory projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | MiroFish | 76,931 |
| 2 | ai-agent-book | 52,623 |
| 3 | cognee | 31,578 |
| 4 | Memori | 17,149 |
| 5 | memU | 14,527 |
| 6 | Semantica | 13,893 |
| 7 | honcho | 7,563 |
| 8 | EverOS | 3,563 |
| 9 | memsearch | 2,729 |
| 10 | memanto | 2,321 |
| 11 | iai-personal-memory-engine | 906 |
| 12 | awesome-harness-engineering | 896 |
| 13 | create-context-graph | 731 |
| 14 | Awesome-Agent-Memory | 670 |
| 15 | m_flow | 539 |
| 16 | activity-frames | 531 |
| 17 | memtrace-public | 488 |
| 18 | PRO-LONG | 456 |
| 19 | Statewave | 271 |
| 20 | piia-engram | 163 |
| 21 | altk-evolve | 122 |
| 22 | deepmem | 114 |
| 23 | open-index | 112 |
Sponsored
AppSignal knows why the f*#k it crashed.
Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
www.appsignal.com