Agent memory
Memory for agents, teams, and people so agents can recall what a company knows and what they just did.
Open-source memory system for agents and teams. It connects company sources such as Slack, GitHub, and Linear so agents can recall shared context through one memory API, an SDK, or an MCP server, with an optional Cognee Cloud for managed scale.
Interface
mcpModel Context Protocol server
Interface
httpHTTP API
[ Observed sample ]
The count is distinct observed stacks. It is not a Score input.
This component is not in Leyline's observed sample.
Record cmp_cognee
[ Score explain ]
Score v2 uses only observed signals. The displayed contribution is weight × value × 100. Missing factors are insufficient evidence.
Score factor
GitHub health18% weight. insufficient evidence
insufficient evidence
insufficient evidence
insufficient evidence
Score factor
Agent use16% weight. insufficient evidence
insufficient evidence
insufficient evidence
insufficient evidence
Score factor
Human notes14% weight. insufficient evidence
insufficient evidence
insufficient evidence
insufficient evidence
Score factor
Composability16% weight. insufficient evidence
insufficient evidence
insufficient evidence
insufficient evidence
Score factor
Checklist10% weight. An MCP surface is declared. An API is declared. Cost is unknown. 2 of 3 checklist fields are complete.
Value 0.67 · 6.7 points
10% weight × 0.67 value
An MCP surface is declared. An API is declared. Cost is unknown. 2 of 3 checklist fields are complete.
Score factor
Evidence quality14% weight. 1 sources cover 1 evidence types. The latest dated evidence is 2026-10-15. Freshness is omitted unless observed as a signal.
Value 0.18 · 2.5 points
14% weight × 0.18 value
1 sources cover 1 evidence types. The latest dated evidence is 2026-10-15. Freshness is omitted unless observed as a signal.
Score factor
Benchmarks12% weight. insufficient evidence
insufficient evidence
insufficient evidence
insufficient evidence
GitHub health: insufficient evidence
Agent use: insufficient evidence
Human notes: insufficient evidence
Composability: insufficient evidence
Benchmarks: insufficient evidence
[ Claims ]
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.
Interface
mcpModel Context Protocol server
Interface
httpHTTP API
audience
AgentsThe product is built for software agents to call, not only for interactive humans.
Agents Browse Agents[ Capability slices ]
Memory for agents, teams, and people so agents can recall what a company knows and what they just did.
Connect Slack, GitHub, and Linear, with first-party integrations for Claude Code, Cursor, LangGraph, OpenClaw, and more.
Agents recall stored context through the memory API or MCP read access.
Inferred from executor
Inferred from executor
The page states one memory API and an SDK, plus an MCP server so compatible agents can read and write Cognee memory without custom glue. It names first-party integrations for Claude Code, Cursor, LangGraph, and OpenClaw, and also lists Codex, Skill, and Hermes. Slack, GitHub, and Linear are named as sources to connect. Auth, rate limits, and API schemas are not specified on this page.
[ Relations ]
[ Signals ]
Signals carry source, method, and observedAt. Source review dates and evidence basis are shown separately. Unobserved metrics stay insufficient evidence.
Evidence basis unknown · Check date unknown · Source date 2026-10-15
No social source is stored.
Propose a change with a public source. Corrections wait for review before the card changes.
[ Notes ]
No notes are stored.