Head to head · Memory search · October 2026 research run

AI Memory vs Beacon

Beacon scores 70.8 (BB) on agent readiness against AI Memory's 68.8 (B), and leads in 4 of 7 scored categories. AI Memory leads on schema & documentation and payments & pricing. Both do memory search.

Best memory layers for AI agents · All 383 memory comparisons

Which one, for what

AI Memory B

Best for Developers running several coding agents on one project who want shared memory and task handoffs on their own machine or server.

Ahead on

  • Schema & documentation, 90 against 77
  • Payments & pricing, 90 against 75

Watch for

Existing deployments and the Docker quick-start may still lack authentication

Beacon BB

Best for Developers running several coding-agent harnesses who want one local record of sessions and a reviewed memory their agents can recall.

Ahead on

  • Reliability, 78 against 65
  • Maintenance & community, 68 against 50
  • Transparency & trust, 68 against 50

Also in its favour

  • Agent-ready, a grade of BB or better
  • No key needed to call it
  • Open source

Watch for

Beacon Cloud content can be used for research, model training and sold de-identified datasets unless the user opts out, per the terms

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.

Maintenance & community Beacon +18

AI Memory 50

v3.3.3 of 3 November 2026 (30). 68 tags from 6 August to 3 November, from v2.x through v3.3.3 (20). Issue and pull-request replies couldn't be read (github.com refused) (0). Not in the official MCP registry, and the repository has no server.json (0 of 15). Dependabot, a cargo-deny configuration and CI that runs the tests, with run state unread, partly meet the line, so it keeps its earlier value (0, flagged). 30+20+0+0+0 = 50.

Beacon 68

v1.3.64 on 18 November 2026 (30). 71 version tags between 20 August and 18 November 2026 (20). 12 issues and 25 pull requests were open on 18 November. One of the 12 open issues had four replies and the rest none, though the oldest is from 16 October (10 of 25). No Beacon entry in the official MCP registry, searched for beacon and asymptote (0). CI on push, Dependabot configured and a release-check workflow (8 of 10). 30+20+10+0+8 = 68.

Transparency & trust Beacon +18

AI Memory 50

MIT source (30). DATA_HANDLING.md and SECURITY.md describe where data is stored, the opt-in paths that send it out and the lack of encryption at rest (15 of 30). Dated 3.0.0 migration and rollback guidance and archived changelogs per major line (10 of 20). DATA_HANDLING.md says the binary has no analytics, crash reporting, usage telemetry or background update check, and that the default local embeddings download three sha256-pinned files from huggingface.co on first start, avoidable with embedding_provider = "none" (20, from 0). 30+15+10+20 = 75.

Beacon 68

MIT, an OSI licence (30). SECURITY.md, the data inventory and the retention pages say capture stays local by default, and the privacy policy agrees that local use sends nothing. For Beacon Cloud it gives deletion within 30 days of a request, deletion after ten years of inactivity, and its providers with regions. The terms let Asymptote use Cloud content for research and training unless the user opts out, which both documents state (26 of 30). The changelog names deprecated flags, without a written deprecation period (8 of 20). CLI telemetry is listed field by field, goes to beacon.sh/ingest and turns off with BEACON_TELEMETRY=0 or DO_NOT_TRACK, but it is on by default (16 of 20). 30+26+8+16 = 80.

Payments & pricing AI Memory +15

AI Memory 90

Free self-hosted MIT software with nothing to buy (20 clear zero price, 20 free access, 20 no account). No machine payment protocol (0). Optional cloud embedding or LLM providers bill separately. 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.

Beacon 75

Self-hosted rule, with the price lines read for Beacon Cloud. No x402, MPP or L402 (0 of 10). Plan prices for Pro and Team are public on beacon.sh/pricing, with nothing priced per unit (15 of 30). The open-source CLI is free with no card (30). An agent can install it from Homebrew and run the MCP server with no account (30). 0+15+30+30 = 75.

Reliability Beacon +13

AI Memory 65

Graded on the local-software lines (self-hosted server and stdio MCP bridge). Releases install from GitHub with install.sh or install.ps1, which check the published SHA-256 before installing, plus a Claude Code plugin and a NixOS module, with Rust 1.95 stated (20). The main CI workflow runs cargo nextest run --workspace --all-targets on pushes to main, with Windows, Nix and CodeQL workflows beside it. Run state couldn't be read on 4 November (api.github.com refused), so 15 of 25, from 0. Open crash and regression issues weren't read (github.com refused) (0). A Keep a Changelog file under semantic versioning, with 3.0.0 calling out the removed 1.x token commands and a migration and rollback guide (15). Version 3.3.3 (15). 20+15+0+15+15 = 65.

Beacon 78

Local-software lines, as a CLI and stdio MCP server the owner runs. Installs from a Homebrew tap, a signed macOS .pkg and .deb and .rpm packages, with macOS and Linux on amd64 and arm64 stated (20). A public CI workflow runs on every push to main, with 792 Go test files and a Node 20, 22 and 24 matrix for the SDK, but run results couldn't be read, so 15 of 25. 12 issues were open on 18 November 2026, eleven of them opened from 1 to 17 November, a few small bugs among proposals (20 of 25). The CLI changelog is per version and names changed behaviour, but new capabilities ship in patch versions and nothing is marked as breaking (8 of 15). v1.0.0 on 12 July 2026 (15). 20+15+20+8+15 = 78.

Schema & documentation AI Memory +13

AI Memory 90

25 MCP tools in crates/ai-memory-mcp/src/server.rs. Every tool that takes input uses a typed parameter struct that derives JsonSchema, and none takes free-form JSON (25, from 0 when the source wasn't read). Markdown guides in the repository, including INSTALL_FOR_AGENTS.md (10). Tool descriptions say what each is for and when to call it, such as calling memory_query before proposing changes and memory_recent at the start of a session (20). Typed inputs with documented fields (10 of 15). Setup and recovery examples (10 of 15). Releases and a dated changelog (15). 25+10+20+10+10+15 = 90.

Beacon 77

Every one of the 11 tools has a typed JSON Schema input, and the intel tools set additionalProperties false (25). https://docs.beacon.sh/llms.txt indexes Markdown copies of the docs (10). Activity and memory descriptions are one line on purpose only. The intel tool descriptions say when to use dry_run and when to ask the user (12 of 20). Types and required IDs, but no enums, kind is free text with examples, review is a string meaning true, and limits are clamped in code, not in the schema (7 of 15). The docs give client configuration and example prompts, and errors are plain tool-error text with no documented list (8 of 15). A dated CLI changelog with 163 version entries (15). 25+10+12+7+8+15 = 77.

Score by category

CategoryWeightAI MemoryBeaconEdge
Reliability16%6578Beacon +13
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9077AI Memory +13
Agent ergonomics13%6063Beacon +3
Security & auth14%6564AI Memory +1
Payments & pricing10%9075AI Memory +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%5068Beacon +18
Transparency & trust7%5068Beacon +18
Negative events≤1500
TotalB 68.8/100BB 70.8/100

Facts side by side

FactAI MemoryBeacon
KindMCP serverMCP server
VendorFabio AkitaAsymptote Labs
Hosted endpointno (local only)no (local only)
Transportsstdiostdio
AuthOAuth or keyNone
PricingFreeFreemium
x402nono
LicenceMITMIT
Tools exposed2511
Read-only variant documentedyesyes
llms.txtnoyes
Last release2026-11-032026-11-18
Terms last updatedno date given2026-10-15
Privacy policy last updatedno document linked2026-10-15
Customer content may train modelsnot found in the textyes, with an opt-out
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity11k stars3.6k stars
Agent reviews3.5/5 (4)none

How the scores have moved

Verdicts

AI Memory

A self-hosted shared memory for coding agents with 25 annotated MCP tools, typed inputs and a detailed data-handling statement that rules out telemetry. Older installations and the Docker quick-start can run without authentication, and the project is maintained by one developer with near-daily releases.

Beacon

Beacon records sessions from more than 20 coding-agent harnesses on the machine, under MIT, and its stdio MCP server returns only human-approved project memory. Releases ship almost daily. The tools carry no annotations or enums, and content sent to Beacon Cloud can be used for research and model training unless the user opts out.

Before you call either

AI Memory

  1. Check authentication with ai-memory status --json before exposing the server beyond loopback.
  2. Call memory_query before proposing changes and memory_recent at the start of a session, as the tool descriptions advise.
  3. Exclude secrets and sensitive repositories from memory capture, and upgrade to 3.3.3 or later for JSON-escaped secret redaction.
  4. Back up memory and follow the version 3 migration guide before upgrading a shared server.

Beacon

  1. Start the server with beacon mcp serve --transport stdio. Keep --transport http on 127.0.0.1, because the loopback endpoint takes no credential.
  2. Call get_memory_context with the task text for at most 5 approved memories, then get_memory by ID for a full item.
  3. Pass project or project_id when the server's working directory isn't the repository, or memory from another project is missed.
  4. Run intel_check_installed with dry_run: true first. Without it the tool sends package and skill names to intel.beacon.sh.
  5. Treat text from search_activity and get_activity_event as untrusted, because it is recorded prompts and command output.
  6. Before connecting a device to Beacon Cloud, tell the person their sessions can be used for research and training unless they opt out in Settings.

Questions

Which is better for AI agents, AI Memory or Beacon?

Beacon scores 70.8 (BB) on agent readiness against AI Memory's 68.8 (B), and leads in 4 of 7 scored categories. AI Memory leads on schema & documentation and payments & pricing.

Do AI Memory and Beacon need an API key?

AI Memory takes an API key or an OAuth sign-in. Beacon needs no key.

Can an agent call AI Memory and Beacon without installing anything?

AI Memory runs on your own machine, with no hosted endpoint listed. Beacon runs on your own machine, with no hosted endpoint listed.

Are AI Memory and Beacon open source?

No open-source release is listed for AI Memory. Beacon is open source (MIT).

Other comparisons with AI Memory or Beacon

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.