Item detail
github.com

getzep/graphiti

RepoRadar surfaced getzep/graphiti — a code repository — into the Agent memory section, where it sits at Gold tier with a 'try now' verdict. It is written primarily in Python. Its strongest signal is workflow potential, scored 10.0 out of 10.

Score8.6
Popularity100.0
Riskconditional
TierGold
Score breakdown
Usefulness8.8
Novelty8.0
Momentum8.7
Maturity8.8
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease4.2

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Graphiti belongs on RepoRadar because agent memory is moving from chat history toward structured, queryable context. The repo has strong adoption, Apache-2.0 licensing, active commits, current docs, graph backends, package metadata, Docker support, and a clear boundary between the OSS core and Zep's managed enterprise platform. The caveat is operational: teams still need to run a graph database

Who should use it

Teams building long-lived agent memory with time-aware facts RAG builders comparing graph retrieval against chunk-only retrieval Infrastructure teams that can operate Neo4j or FalkorDB and want an OSS context-graph core

Who should skip it

Hold off on getzep/graphiti if the setup requirements exceed what your current workflow or team can support without dedicated engineering time.

About this signal

getzep/graphiti is tracked by RepoRadar as a code repository in the Agent memory section. First seen 2026-07-11; the source record was last checked on 2026-07-11. The current verdict is 'try now' with a Gold tier and hard setup difficulty. Across RepoRadar's eight signals, getzep/graphiti is strongest on workflow potential (10.0) and practical usefulness (8.8) and weakest on setup ease (4.2) — a profile worth weighing against your own priorities. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The getzep/graphiti record combines a 8.6/10 composite score with separate popularity (100.0), risk (conditional), and setup (hard) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

Context graphs may store user interactions, enterprise facts, and source provenance; start with non-sensitive data and define retention rules before production use; PyPI package depends on provider and graph-database integrations, including OpenAI and Neo4j; verify telemetry, provider-key, and database-access boundaries before deployment.

Evidence links
Closest alternatives / related signals
agent-memory knowledge-graph graph-rag rag mcp-server temporal-graph neo4j falkordb
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-08-13T20:20:15Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

26 dated snapshots retained from 2026-07-11 through 2026-08-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.6 current · +0.0 net
Repository momentum9.6 current · +0.9 net
GitHub stars (observed)29,891 current · +1,278 net
GitHub stars29,891 exact observation
Versionv0.29.3
Last release2026-07-27T20:57:23Z
Maintenanceactive
Current riskconditional
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-138.69.629,891conditionaltry nowactive
2026-08-128.69.629,857conditionaltry nowactive
2026-08-118.69.629,772conditionaltry nowactive
2026-08-108.69.629,728conditionaltry nowactive
2026-08-098.69.629,697conditionaltry nowactive
2026-08-088.69.629,676conditionaltry nowactive
2026-08-078.69.629,499conditionaltry nowactive
2026-08-068.68.729,628conditionaltry nownot recorded
2026-08-058.68.729,591conditionaltry nownot recorded
2026-08-048.69.629,499conditionaltry nowactive
2026-08-038.69.629,499conditionaltry nowactive
2026-08-028.69.629,464conditionaltry nowactive

Why the record changed

stars changed

Stars changed: 29857 → 29891.

stars changed

Stars changed: 29772 → 29857.

stars changed

Stars changed: 29728 → 29772.

stars changed

Stars changed: 29697 → 29728.

stars changed

Stars changed: 29676 → 29697.

stars changed

Stars changed: 29499 → 29676.

stars changed

Stars changed: 29628 → 29499.

stars changed

Reconstructed from adjacent retained daily snapshots; no upstream cause is inferred. Stars changed: 29591 → 29628.

stars changed

Reconstructed from adjacent retained daily snapshots; no upstream cause is inferred. Stars changed: 29499 → 29591.

stars changed

Stars changed: 29464 → 29499.

stars changed

Stars changed: 29420 → 29464.

stars changed

Source-observed stars changed: 29409 → 29420. This reports the retained observation delta and does not infer why the upstream change occurred.