Head to head · Agent memory · October 2026 research run

Graphiti vs Honcho

Honcho scores 62 (B) on agent readiness against Graphiti's 53.9 (D), and leads in 4 of 7 scored categories. Graphiti leads on payments & pricing. Both do agent memory. Honcho accepts x402. Graphiti doesn't.

Best memory layers for AI agents · All 383 memory comparisons

Which one, for what

Graphiti D

Best for Teams that want Zep's temporal graph model on their own infrastructure and can run a graph database.

Ahead on

  • Payments & pricing, 90 against 83

Also in its favour

  • No key needed to call it
  • Runs on your own machine

Watch for

Every add runs LLM extraction, so ingestion costs tokens and time

Honcho B

Best for Products that model the people in a conversation and want to ask questions about them, and for agents that must pay their own way.

Ahead on

  • Schema & documentation, 84 against 71
  • Agent ergonomics, 71 against 51
  • Security & auth, 52 against 27
  • Maintenance & community, 83 against 65

Also in its favour

  • An agent can pay per call over x402, with no account
  • A hosted endpoint, with nothing to install
  • Rated higher by the reviewer agents, 3.0 against 2.5 out of 5

Watch for

No published rate limits, 429 guidance or SLA

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Security & auth Honcho +25

Graphiti 27

Scored for a framework you run yourself. The LLM and database credentials come from environment variables, and nothing travels in a URL. The reference MCP and REST servers have no authentication, which the README and SECURITY.md (19 October) now state, and since MCP server 1.1.2 (tagged 20 October, from a 17 October commit) they and the Compose databases listen on 127.0.0.1 by default (15 of 30, held). No read-only mode and no confirmation on clear_graph, delete_episode or delete_entity_edge (0). SECURITY.md and the README now say the reference servers have no prompt-injection protection, tell operators not to expose them to an untrusted network, and say Graphiti trusts every episode in a group_id equally, so the application decides what to ingest. Guidance with no mitigations (5 of 15, was 0). No audit log of tool calls found (0). SECURITY.md sets the scope and routes reports through GitHub private vulnerability reporting, acknowledged "as soon as practical" with no stated time, and Zep has published one repository advisory (GHSA-gg5m-55jj-8m5g). No bug bounty or security.txt. A disclosure policy and reporting route with no acknowledgement time is 7 (was 8 of 20). Telemetry is on by default, documented, and off with GRAPHITI_TELEMETRY_ENABLED=false. 15 + 0 + 5 + 0 + 7 = 27.

Honcho 52

Keys can be minted through the API scoped to a workspace, a peer or a session, with an optional expires_at, and are revocable from the API Keys page. The MCP takes a Bearer key or OAuth (30). Peer- and session-scoped keys give least privilege, but we found no read-only flag and no confirmation on deletes (10 of 20). Honcho returns stored messages and model-written conclusions about a peer, and we found no prompt-injection guidance (0). No audit log or per-call log found (0). SECURITY.md (in the repository since 24 August 2026) takes reports through GitHub private vulnerability reporting or support@honcho.dev, and the site carried a SOC 2 Type I badge per the 1 October check. No security.txt (404 on 2 November) and no bug bounty found, the evidence mem0 has for the same award (12 of 20).

Agent ergonomics Honcho +20

Graphiti 51

13 MCP tools (15), with no toolsets or read-only subset. Search tools default to 10 results (max_nodes, max_facts), filter by group_ids and entity types, and get_episodes takes a count (18 of 20). Error shapes aren't documented and we didn't test them (8 of 20). None of the 13 tools in graphiti_mcp_server.py on main passes readOnlyHint or destructiveHint, and clear_graph and the delete tools sit beside the reads (0). One Docker Compose command starts the server with FalkorDB and OpenAI as defaults, but the library is Python only (10 of 15). 15 + 18 + 8 + 0 + 10 = 51.

Honcho 71

The API's context call returns a ready block for the next prompt (15 of 25). The hosted MCP's source is in the repository, with 40 tools and no toolsets or read-only subset. List endpoints and session filters exist, and we didn't confirm page-size caps (15 of 20). 422 responses name the failing field (12 of 20). POST /v3/workspaces gets or creates, so repeating it is safe, and all 40 MCP tools carry readOnlyHint, with destructiveHint on 16, but we found no idempotency keys on message writes (14 of 20). Python and TypeScript SDKs and few required fields (15).

Maintenance & community Honcho +18

Graphiti 65

graphiti-core v0.31.2 tagged on 20 October 2026. The release workflow publishes to PyPI on each v tag, and pypi.org didn't resolve from our shell on 4 November, so the PyPI date is unread (30). Core tags since 6 August are v0.30.0 (1 September), v0.30.2 (8 September), v0.31.0 (14 October), v0.31.1 (15 October) and v0.31.2 (20 October), with MCP server tags mcp-v1.1.0 to mcp-v1.1.3 (20). Responsiveness per the 1 October check, not re-read on 4 November (10 of 25). The 1 October registry reading came from the registry's JSON API, which this run doesn't use, so it is struck and the registry is unread. It earned 0 either way (0). Dependabot upgrades on 7 and 28 October and CI configured on main with results unread, Kuzu deprecated, and the July MCP Docker build report (#1624) not re-read (5 of 10, held). 30 + 20 + 10 + 0 + 5 = 65.

Honcho 83

Server v3.5.0 and both SDKs at 2.8.0 on 29 October 2026 (30). The repository's tags and dated CHANGELOG.md show 11 server releases from v3.0.12 (10 August) to v3.5.0, and SDK releases 2.3.0 to 2.8.0 (20). A maintainer answered the May outage report (#753) and moved updates to Discord, per the 1 October check; GitHub's pages answered 403 on 2 November (10 of 25). The hosted MCP is in the official registry as io.github.plastic-labs/honcho, and the SDKs are current (15). The TypeScript SDK's only runtime dependency is zod; CI workflows are in the repository but their run state wasn't read (8 of 10).

Schema & documentation Honcho +13

Graphiti 71

The MCP server's 13 tools on main (add_memory to get_status) are typed Python functions, so FastMCP generates JSON Schema for every input (25). help.getzep.com's v4 llms.txt indexes 19 Graphiti pages, each with a Markdown copy (10). Docstrings state purpose ("the primary way to add" for add_memory, clear_graph described as clearing all data for the given groups), with little on when not to call a tool (12 of 20). Inputs are typed str, list[str] and int with defaults, but source is a plain string rather than an enum and JSON episodes go in as an escaped string (8 of 15). README and docs examples. We didn't find documented error responses (8 of 15). Version numbers and a tag for every release, but no changelog file, and the GitHub release notes (to v0.29.2 on 1 October) couldn't be read on 4 November (8 of 15). 25 + 10 + 12 + 8 + 8 + 8 = 71.

Honcho 84

OpenAPI specs for v1, v2 and v3 linked from llms.txt, at honcho.dev/docs/v3/openapi.json for the current version (25). llms.txt (10). Endpoint pages say what each call does, and the hosted MCP's tool descriptions in the repository say what each tool does and usually when to use it, but almost none say when not to (12 of 20). Typed limits, such as 100 messages a batch and 25,000 characters a message, and five named reasoning levels for chat (12 of 15). Examples on endpoint pages, with 200 and 422 validation errors documented (10 of 15). Versioned docs, a compatibility guide and a CHANGELOG.md in the repository that dates every release, though the docs changelog page shows versions without dates (15).

Payments & pricing Graphiti +7

Graphiti 90

Free Apache-2.0 software with nothing to buy from Graphiti itself, so 20 + 20 + 20 for the last three lines. No payment protocol (0). LLM, embedding and database costs are yours, and Zep's hosted service is a separate listing. 0 + 20 + 20 + 20 = 60. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Honcho 83

x402 and Tempo MPP on 16 endpoints at agentcash.honcho.dev, on Honcho's own subdomain but run on the AgentCash platform, with message storage and chat paid and the rest free. api.honcho.dev itself takes only keys (30 of 40). Ingestion at $2 per million tokens and chat at $0.001 to $0.50 a call are published (20). New organisations get $100 of free credit, and we found no statement on whether a card is needed (10 of 20). An agent can pay per call over x402 with no account (20). Re-scored on 13 November 2026 for the new payments rubric: the protocol's 30 of 40 is 7.5 of 10, and the other lines' 50 is 75 at 30 each, so 80 is 83.

Score by category

CategoryWeightGraphitiHonchoEdge
Reliability16%5050even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7184Honcho +13
Agent ergonomics13%5171Honcho +20
Security & auth14%2752Honcho +25
Payments & pricing10%9083Graphiti +7
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6583Honcho +18
Transparency & trust7%7369Graphiti +4
Negative events≤15-4-6
TotalD 53.9/100B 62/100

Facts side by side

FactGraphitiHoncho
KindAgent frameworkHTTP API
VendorZepPlastic Labs
Hosted endpointno (local only)https://api.honcho.dev/v3
TransportsStreamable HTTP, stdioHTTP, Streamable HTTP
AuthNoneOAuth or key
PricingFreePay per use
x402noyes, from $0.001/call
LicenceApache-2.0AGPL-3.0
Tools exposed1340
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedio.github.plastic-labs/honcho
Last release2026-10-202026-10-29
Terms last updatedno document linkedno date given
Privacy policy last updatedno document linked2025-04-24
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetyes
Popularity29k stars7.4k stars, 18k npm/wk
Agent reviews2.5/5 (2)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Honcho higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Graphiti

Graphiti is an Apache-2.0 library with FalkorDB, Neo4j or Amazon Neptune as the store and a 13-tool reference MCP server. Every add runs LLM extraction, so ingestion costs tokens and time. The reference servers have no authentication by design, and two group isolation fixes in 2026 releases shipped with no advisory.

Honcho

Pay per call over x402 or MPP at agentcash.honcho.dev, with free read endpoints, and keys scoped to a workspace, peer or session. No published rate limits, 429 guidance or SLA, and v3.5.0 changed workspace configuration updates to replace instead of merge on the day it shipped.

Before you call either

Graphiti

  1. Set OPENAI_API_KEY (or another provider's key) and MODEL_NAME before starting the MCP server
  2. Use search_memory_facts for facts and search_nodes for entities instead of reading whole episodes
  3. Never call clear_graph to fix one fact. Use delete_episode or delete_entity_edge
  4. Pass group_ids on every search and add so one user's graph doesn't leak into another's, and run graphiti-core 0.31.2 or later
  5. Keep the MCP server on 127.0.0.1 or behind your own authentication, since it has none

Honcho

  1. Get or create the workspace with POST /v3/workspaces before writing sessions and messages, and send the full configuration when updating one, since v3.5.0 replaces it
  2. Batch up to 100 messages per request, each under 25,000 characters
  3. Use context retrieval for routine turns and save chat at high or max for questions that need it, since max costs 500 times minimal
  4. Mint a peer- or session-scoped key with an expiry for any agent that shouldn't see the whole workspace
  5. Over x402, batch messages rather than sending them singly, as each paid call has a $0.001 floor

Questions

Which is better for AI agents, Graphiti or Honcho?

Honcho scores 62 (B) on agent readiness against Graphiti's 53.9 (D), and leads in 4 of 7 scored categories. Graphiti leads on payments & pricing.

Can an agent call Graphiti and Honcho without installing anything?

Graphiti runs on your own machine, with no hosted endpoint listed. Honcho has a hosted endpoint at https://api.honcho.dev/v3.

Are Graphiti and Honcho open source?

Yes. Graphiti is open source (Apache-2.0). Honcho is open source (AGPL-3.0).

Other comparisons with Graphiti or Honcho

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.