AI · alternatives · 2026

24 alternatives to Fixing LLM memory degradation in long coding sessions

Long-session LLM memory degradation (entropy) is the silent killer of complex coding projects. Models like Gemini, GPT-4, and Claude all suffer from it, leading to hallucinations and lost context. I've developed an open-source protocol that temporarily "fixes" this issue by structuring the dialogue. It's not the final architectural solution, but it’s a proven patch for developers working right now. Looking for feedback from the community on how we can solve this structurally. https://github.com/robertomisuraca-blip/LLM-Entropy-Fix-Prot...

Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.

1
Stop Claude Code from forgetting everything▲202
I got tired of Claude Code forgetting all my context every time I open a new session: set-up decisions, how I like my margins, decision history. etc. We built a shared memory layer you can drop in as a Claude Code Skill. It’s basically a tiny memory DB with recall that remembers your sessions. Not magic. Not AGI. Just state. Install in Claude Code: /plugin marketplace add https://github.com/mutable-state-inc/ensue-skill /plugin install ensue-memory # restart Claude Code What it does: (1) persists context between sessions (2) semantic & temportal search (not just…
Dec 2025 · github.com · its alternatives →
2
Agentmemory▲310
Persistent memory for Claude Code, Codex & coding agents
May 2026 · agent-memory.dev · its alternatives →
3
DeltaMemory▲104
Most AI agents forget everything between sessions. We built DeltaMemory to fix that. It's a cognitive memory layer that gives agents persistent recall, automatic fact extraction, and temporal reasoning — via a single SDK call. Key numbers: - 89% accuracy on LoCoMo long-term conversation benchmark - 50ms p50 retrieval latency - 97% cost reduction vs raw token re-processing Open source SDKs, works with any LLM stack. Currently in early access. Happy to answer questions about the architecture, benchmark methodology, or how we handle knowledge graphs.
Feb 2026 · deltamemory.com · its alternatives →
4
Claude Memory – Long-term memory for Claude▲76
OpenMemory Chrome Extension: Long-term memory for ChatGPT, Claude, Perplexity, Grok etc - mem0ai/mem0-chrome-extension
2024 · github.com · its alternatives →
5
Yet another memory system for LLMs▲165
Built this for my LLM workflows - needed searchable, persistent memory that wouldn't blow up storage costs. I also wanted to use it locally for my research. It's a content-addressed storage system with block-level deduplication (saves 30-40% on typical codebases). I have integrated the CLI tool into most of my workflows in Zed, Claude Code, and Cursor, and I provide the prompt I'm currently using in the repo. The project is in C++ and the build system is rough around the edges but is tested on macOS and Ubuntu 24.04.
2025 · github.com · its alternatives →
6
GPS▲83
Memory layer for LLMs that stores repo rules + past lessons
May 2026 · github.com · its alternatives →
7
Total Recall – write-gated memory for Claude Code▲67
built this because I got tired of re-teaching Claude Code the same context every session. Preferences, decisions, “we already tried X,” “don’t touch this file,” etc. After a few days it starts to feel like onboarding the same coworker every morning. Most “agent memory” tools auto-save everything. That feels good briefly, then memory turns into a junk drawer and retrieval gets noisy. Total Recall takes the opposite approach: a write gate. Before anything gets promoted, it asks one question: “Will this change future behavior?” If not, it doesn’t get saved. How it works: Daily log first (raw…
Feb 2026 · github.com · its alternatives →
8
Open-source model and scorecard for measuring hallucinations in LLMs▲65
Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple" instruction like "summarize the following news article," every LLM that's available hallucinates to some extent, making up details that never existed in the source article -- and some of them quite a bit. As a RAG provider and proponents of ethical AI, we want to see LLMs get better at this. We've published an open source model, a blog more thoroughly describing our methodology (and…
2023 · vectara.com · its alternatives →
9
A local-first memory store for LLM agents (SQLite)▲48
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. - CaviraOSS/LongMemory
Dec 2025 · github.com · its alternatives →
10
toktrack▲68
Did you know Claude Code deletes your session data after 30 days? I found out the hard way when I tried to check my spending history. My session files hit 3GB (2000+ files) and existing tools took 40+ seconds. Rewrote it in Rust with simd-json + rayon. - First run: ~1s (vs 40s+) - Daily use: ~0.04s (1000x faster, cached) - TUI dashboard with daily/weekly/monthly breakdown - Supports Claude Code, Codex CLI, Gemini CLI - Persistent cache — history survives even after CLI deletes files GitHub: https://github.com/mag123c/toktrack Feedback welcome!
Feb 2026 · github.com · its alternatives →
11ZL
Zep – Long-Term Memory Store for LLM Apps▲7
Zep is a long-term memory store designed for conversational AI applications built using modern LLMs. It handles the storage, summarization, embedding, indexing, and enrichment of chat histories, and offers developers a simple, low-latency API to this data. Chat history storage is an infrastructure challenge all developers and enterprises face as they look to move from prototypes to deploying conversational AI applications that provide rich and intimate experiences to users. Key features include long-term memory persistence, auto-summarization, vector search, auto-token counting, and Python…
2023 · its alternatives →
12CM
CodeYam Memory – comprehensive memory management for Claude Code▲17
We built CodeYam Memory because Claude Code kept making the same mistakes on our codebase. Our claude.md files quickly got stale and maintaining by hand or with Claude wasn’t sufficient. While digging into this we found that Claude has a native rules system that allowed us to target specific parts of our repo with path matching. This was ideal for our use case but trying to manage these rules by hand was already not working and would be even harder with more granular, targeted rules. CodeYam Memory uses a background agent to review your coding session transcripts, identifies confusion…
Mar 2026 · its alternatives →
13
Continual Learning with .md▲34
I have a proposal that addresses long-term memory problems for LLMs when new data arrives continuously (cheaply!). The program involves no code, but two Markdown files. For retrieval, there is a semantic filesystem that makes it easy for LLMs to search using shell commands. It is currently a scrappy v1, but it works better than anything I have tried. Curious for any feedback!
Apr 2026 · github.com · its alternatives →
14
AI Memory Layer for ChatGPT and Claude.▲26
Shared persistent memory across all your LLMs.
2025 · teamlayer.xyz · its alternatives →
15
LLMs can be susceptible to a new kind of malware▲17
New ways of breaking app-integrated LLMs . Contribute to greshake/llm-security development by creating an account on GitHub.
2023 · github.com · its alternatives →
16
Ctrlb-decompose: Strip the noise from logs before sending to LLMs▲14
LLM-ready reasoning surface over logs. Contribute to ctrlb-hq/ctrlb-decompose development by creating an account on GitHub.
Sep 2026 · github.com · its alternatives →
17IL
Improve LLM Performance by Maximizing Iteration Speed▲5
LLM Application development is extremely iterative, more so than any other types of development. This is because in addition to all the activities involved in regular application development, we also need to make the LLM Application accurate and reduce hallucination. To improve performance, we need to trial and error various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt context with different RAG architecture, try different agent architecture, and more. There are thousands of permutations to try. We need to be able to easily experiment with these…
2024 · palico.ai · its alternatives →
18
Breathe-Memory – Associative memory injection for LLMs (not RAG)▲6
LLMs forget. The standard fix is RAG — retrieve chunks, stuff them in. It works until it doesn't: irrelevant chunks waste tokens, summaries lose structure, and nothing actually models how memory works. Breathe-memory takes a different approach: associative injection. Before each LLM call, it extracts anchors from the user's message (entities, temporal references, emotional signals), traverses a concept graph via BFS, runs optional vector search, and injects only what's relevant — typically in <60ms. When context fills up, instead of summarizing, it extracts a structured graph: topics,…
Mar 2026 · github.com · its alternatives →
19
Long term Memory and 50M token window for LLM▲6
Join the discussion on this paper page
14d ago · huggingface.co · its alternatives →
20
Llmbuffer – Python library for cache-optimized LLM conversation history▲7
I was not getting good cache utilization when including dynamic context in agent threads. After a lot of experimentation, I found a good pattern that minimizes how often long lived conversation history gets modified while still supporting dynamic context. It has flexible hooks for doing things like truncating or summarizing tool outputs when transitioning messages to the long term history. And I'm seeing >>90% of tokens hitting the cache for my agents despite including a lot of dynamic user context. There are a wide range of agent prompting strategies so I'd love to hear where this library…
Jun 2026 · github.com · its alternatives →
21
LLM Memory Storage that scales, easily integrates, and is smart▲6
I built a super easy to integrate memory storage and retrieval system for NodeJS projects because I saw a need for information to be shared and persisted across LLM chat sessions (and many other LLM feature interactions). I tried to keep the barrier to use as low as possible so I included built-in support for major LLMs (GPT, Gemini, and Claude) as well as major vector store providers (Weaviate and Pinecone). The memory store works by ingesting and automatically extracting “memories” (summarized single bits of information) from LLM interactions and vectorizing those. When you want to provide…
Mar 2026 · github.com · its alternatives →
22AS
A surprisingly effective way to predict token importance in LLM prompts▲14
We explored a novel method to gauge the significance of tokens in prompts given to large language models, without needing direct model access. Essentially, we just did an ablation study on the prompt using cosine similarity of the embeddings as the measure. We got surprisingly promising results when comparing this really simple approach to integrated gradients. Curious to hear thoughts from the community!
2023 · heatmap.demos.watchful.io · its alternatives →
23
Global Issue Memory MCP▲9
Hey HN, I built Global Issue Memory (GIM), an open-source MCP server that lets AI coding assistants look up and share solutions to errors they encounter. GitHub: https://github.com/timho102003/global-issue-memory Try it: https://www.usegim.com/docs/getting-started (free, no signup required to use the MCP tools) How I got here: I do a lot of vibe coding where I prompt Claude Code and let it run autonomously. I kept noticing the same pattern: the AI would hit a common error, spend 30K+ tokens doing web searches and trying failed fixes, and by the time it…
Feb 2026 · usegim.com · its alternatives →
24
Llongterm▲12
The missing memory layer for generative AI
2024 · llongterm.com · its alternatives →

Also compare

Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →