|
Cards — lasting memory for your AI agents
Your AI forgets your project every session — what you decided, what you ruled out, what’s still open. Cards gives your project a memory that lasts, and your...
|
87 % |
|
Hunch — A shared record for AI agents
Keep decisions, completed work, and commitments available to AI agents, with their sources. Git-native engineering memory and a self-hosted state server.
|
87 % |
|
Shared Memory for teams · Keel
Your agents keep forgetting what your team already decided. Keel is the one place that memory lives.
|
86 % |
|
MaguraIAbs — your AI remembers, and answers for it
One context for every coding session, and a verdict on each: what was claimed, checked against git and the running box.
|
85 % |
|
comemory — a task tracker where your coding agents are assignees
Claude Code, Codex and Cursor as assignees. Each run records what it decided, what failed and what to watch for, so the next one starts from a handoff. Join...
|
85 % |
|
Trail - everything your agent finished, skipped, and decided
Nothing in your project stays half-done. Trail is the tracker your coding agent writes to itself, and the next session opens knowing what the last one learned.
|
85 % |
|
AI Agent Memory That Works Across Sessions | Ratifa
Give your AI agents persistent project memory. Ratifa remembers decisions, progress, context and next steps so your AI can pick up where it left off.
|
84 % |
|
Hivemind — Run agents in parallel. Break nothing.
Hivemind runs coding agents side by side, keeps each one in its lane, and stops bad changes before they hit your branch.
|
84 % |
|
Astryke — your projects remember themselves
Astryke keeps every project current so every connected AI session starts knowing where you left off and what you already decided. Your AI forgets. Astryke do...
|
84 % |
|
Spegling — One AI, yours.
One memory across every session and every agent you use, real walls between your work and private lives, a record of everything it did, and the discipline to...
|
84 % |
|
declr
declr gives your coding agents a shared record of tasks, decisions, ownership and handoffs. They can pick up the work, coordinate with each other and leave a...
|
84 % |
|
Atman — Continuous Identity for AI Agents
Open-source psychological layer for LLM agents: experiential memory, reflection, and continuity across sessions—not just retrieved facts.
|
84 % |
|
See your clients whole
Write notes your way. Before the next session, the pre-session glance reads your prior notes back to you. The note is built from what you actually said.
|
84 % |
|
Edge CLI — what your agent calls when it gives up
Edge reads a failed agent session, distills the failure into a portable, uncontaminated package, fans it across several harnesses in parallel, and shows you...
|
84 % |
|
kadence: shared memory for coding agents, in your git repo
Tasks, decisions and notes as events in your git repo. Your team and its coding agents read the same record. MIT, $0, no server, no network.
|
84 % |
|
Conderis • Reviewed knowledge for coding agents
Shared context for coding agents, with a review step. Decisions, tasks and project instructions reach every agent only after a maintainer approves them.
|
83 % |
|
forefetch: memory that answers before the question
Anticipatory memory for multi-agent pipelines. forefetch learns your pipeline's rhythm and has context at the agent's side before it asks. Measured, not clai...
|
83 % |
|
Alike — The semantic web for your agents.
Alike is how your coding agents brief each other without going through you. It runs under Claude Code, Codex and Cursor, and starts every session with what y...
|
83 % |
|
Hebbrix - Persistent Memory for AI Agents
Build AI agents with persistent memory in minutes. Hebbrix provides production-ready memory infrastructure so your agents remember, learn, and improve - with...
|
83 % |
|
Hatley Agent Studio — walk into every client meeting already briefed
One shared, living brief per client and a Briefing Agent that keeps it current on your behalf — for coaches, consultants, planners and counsel. Every session...
|
83 % |
Detected social media networks