Tools

Memory tools for coding agents

Coding agents start each session with an empty context, so you end up re-explaining the codebase, past decisions and conventions. These projects store what the agent learned and feed the relevant parts back in, through hooks, MCP servers or a memory API.

Approaches range from plain Markdown notes to knowledge graphs and vector stores. Lighter tools are easier to inspect and edit by hand; heavier ones recall more across large projects but add a service to run.

Repos tracked
81
New this week
+3
added to the list
Stars gained in 30 days
+94.4k
across 60 ranked repos
Updated
Oct 17, 2026

Rising newcomers

21 newcomers

Created in the last 90 days and gaining at least 20 stars this week.

Harvil1/codeAgentOpen Harvil1/codeAgent on GitHub (opens in new tab)

New

CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.

+602this week Created 15 days ago

sno-ai/sno-stationOpen sno-ai/sno-station on GitHub (opens in new tab)

New

Turn the agents you already use into a squad. Codex, Claude Code, Cursor, Hermes Agent and OpenClaw use one encrypted memory, pass work to each other, review each other's work, and dream every night to wake up a little better. Open source. Runs on your computer.

+260this week Created 28 days ago

How this list is ranked

60% momentum, 40% health. Newcomers: created in the last 90 days with ≥ 20 stars this week.

How the score is computed
  • Health (0–100) reflects release cadence, recent commit activity and the number of active contributors.
  • Momentum (0–100) is stars gained in 30 days ÷ √(stars before), scaled within this collection, so a small project growing fast can outrank a large one.
  • Newcomers are listed only in their own block, so a repo never appears twice.
  • Several repos from the same owner are grouped under that owner’s best-ranked project.
  • Members come from matching rules (GitHub topics, keywords in the description and README) plus a short hand-kept include and exclude list. The ranking is recomputed every hour from public GitHub activity.
Related topics AI agentsLLM

Ranking

60 repos

Ranked by momentum, then health

  2. Rank 2

    TencentCloud/OctopOpen TencentCloud/Octop on GitHub (opens in new tab)

    A smarter, self-hosted AI assistant — multi-user, multi-agent.

    Python9.7k stars totalHealth: HealthyAge: 3 mos
    +6.1k stars in 30 days +135% vs previous 30 days Score 97
  4. Rank 4

    thedotmack/claude-memOpen thedotmack/claude-mem on GitHub (opens in new tab)

    Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

    TypeScript101k stars totalHealth: HealthyAge: 13 mos
    +7.4k stars in 30 days +125% vs previous 30 days Score 94
  8. Rank 8

    ruvnet/rufloOpen ruvnet/ruflo on GitHub (opens in new tab)

    🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

    TypeScript75.7k stars totalHealth: HealthyAge: 16 mos
    +3.2k stars in 30 days −31% vs previous 30 days Score 85

Showing 10 of 55 ranked repos. 21 newcomers are listed separately. 5 repos are folded under their owner’s best-ranked project.

Related collections

View all collections