AgentMemory

[ Score explain ]

Why the Score is 3

Score v2 uses only observed signals. The displayed contribution is weight × value × 100. Missing factors are insufficient evidence.

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

insufficient evidence

10% weight × 0.00 value

0.0 points

No MCP surface is declared. No API is declared. Cost is unknown. 0 of 3 checklist fields are complete.

14% weight × 0.18 value

2.5 points

1 sources cover 1 evidence types. The latest dated evidence is 2026-05-08. Freshness is omitted unless observed as a signal.

insufficient evidence

insufficient evidence

insufficient evidence

Total2.54 → 3 after rounding

GitHub health: insufficient evidence

Agent use: insufficient evidence

Human notes: insufficient evidence

Composability: insufficient evidence

Benchmarks: insufficient evidence

[ Claims ]

Publisher-asserted record

Claims are what the publisher declares. Score uses observed signals, not these assertions, except for checklist fields derived from interfaces. MCP, API, cost, and license claims are marked verified, unverified, or contradicted from intake evidence.

Kind: resource
Interfaces: None recorded
Functions: Function
Code
write or edit programs
Code Browse Code

Function
Memory
keep context across turns
Memory Browse Memory

Function
Connect
speak a protocol (MCP, API, CLI)
Connect Browse Connect

[ Capability slices ]

Compose the useful parts.

code

Code

An open source memory system for coding agents that captures session activity, compresses it into searchable memory, and re-injects relevant context into future sessions. The repo positions it as agent-agnostic infrastructure that can work across Claude Code, OpenClaw, Codex CLI, Cursor, Gemini CLI, and other MCP or HTTP-capable agents.

unknownCompose with this

memory

Memory

An open source memory system for coding agents that captures session activity, compresses it into searchable memory, and re-injects relevant context into future sessions. The repo positions it as agent-agnostic infrastructure that can work across Claude Code, OpenClaw, Codex CLI, Cursor, Gemini CLI, and other MCP or HTTP-capable agents.

unknownCompose with this

connect

Connect

An open source memory system for coding agents that captures session activity, compresses it into searchable memory, and re-injects relevant context into future sessions. The repo positions it as agent-agnostic infrastructure that can work across Claude Code, OpenClaw, Codex CLI, Cursor, Gemini CLI, and other MCP or HTTP-capable agents.

unknownCompose with this

[ Relations ]

Derived alternatives and shared slots

Fills the same slot asExecutor Shared functions code, connect. Can fill the same function slot.
Alternative toREA Shared functions code, connect. Same kind and overlapping capability.
Fills the same slot asComparing AI agent sandbox platforms: E2B, Modal, Daytona, and more Shared functions code, connect, memory. Can fill the same function slot.
Fills the same slot asAtomic Agent Shared functions connect, memory. Can fill the same function slot.
Fills the same slot asHow HopX Achieves 100ms Cold Starts Shared functions code, memory. Can fill the same function slot.
Fills the same slot aspen.dev Shared functions code, connect. Can fill the same function slot.
Fills the same slot asOnyx Shared functions code, connect. Can fill the same function slot.
Fills the same slot asAI Agent Sandbox Comparison 2026: Seven Platforms Shared functions code, memory. Can fill the same function slot.

[ Signals ]

Observed evidence

Each signal carries source, method, and observedAt. Unobserved metrics stay insufficient evidence.

humanCompendium resource card

No social source is stored.

[ Notes ]

No notes are stored.

Frequency in Leyline's observed sample

Why the Score is 3

Publisher-asserted record

Compose the useful parts.

Code

Memory

Connect

Derived alternatives and shared slots

Observed evidence