{ "data": { "a": { "slug": "everos", "name": "EverOS", "vendor": "Evermind AI, Inc.", "vendorUrl": "https://evermind.ai", "kind": "http-api", "category": "agent-memory", "summary": "EverOS, formerly EverMemOS, is EverMind's open-source memory runtime for agents. It stores conversations, files and agent trajectories as Markdown with SQLite and LanceDB indexes, behind a local HTTP API and MCP server, with a managed EverOS Cloud.", "url": "https://www.anchorterminal.com/tools/everos", "markdownUrl": "https://www.anchorterminal.com/tools/everos.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/everos.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/everos.json", "dns": "everos.grade.anchorterminal.com", "repo": "https://github.com/EverMind-AI/EverOS", "license": "Apache-2.0", "transports": [ "http", "stdio" ], "packages": [ { "registry": "pypi", "name": "everos" }, { "registry": "pypi", "name": "everos-mcp" } ], "auth": "none", "authNotes": "The self-hosted server has no authentication and binds to 127.0.0.1:8000 by default. The owner supplies LLM and embedding provider keys in ~/.everos/everos.toml. EverOS Cloud uses a bearer API key from the console at everos.evermind.ai, and its hosted MCP connector signs in with an EverOS account.", "pricing": "freemium", "pricingNotes": "Free under Apache-2.0 to run locally, with LLM and embedding costs paid to the chosen provider. EverOS Cloud has a console and API keys, but no plan or price was found on evermind.ai or docs.evermind.ai.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository, the OpenAPI document, llms.txt or the docs (checked 2026-11-06).", "endpoints": [] }, "toolCount": 7, "popularity": { "githubStars": 13839, "npmWeekly": null, "pypiWeekly": 4033, "asOf": "2026-11-06" }, "docsUrl": "https://docs.evermind.ai", "llmsTxt": "https://docs.evermind.ai/llms.txt", "openapi": "https://github.com/EverMind-AI/EverOS/blob/main/docs/openapi.json", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "tags": [ "open-source", "self-hosted", "local", "hosted", "apache-2.0", "python", "mcp", "openapi", "llms-txt", "markdown", "no-auth" ], "lastRelease": "2026-10-22", "graded": true, "anchor": { "graded": true, "score": 69.4, "grade": "B", "agentReady": false, "rank": 247, "ranked": true, "rankOf": 1510, "categoryRank": 6, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 80, "payments": 40, "reliability": 79, "schema": 89, "security": 47, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.", "bestFor": "Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.", "strengths": [ "Apache-2.0 Python library and local server at 1.5.1, with Keep a Changelog entries and semantic versioning declared", "OpenAPI document with 40 operations, every one described, and llms.txt plus llms-full.txt for the docs", "Retryable conditions are typed, such as 503 SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE for a busy database", "Memory is canonical Markdown on disk, editable by hand, with deletion by owner, session or memory id", "SECURITY.md with a five-day acknowledgement, plus a valid security.txt at evermind.ai" ], "weaknesses": [ "The local HTTP server has no authentication and relies on binding to 127.0.0.1", "EverOS Cloud prices, plans and rate limits were not found on any public page", "The MCP server's autonomy protocol tells hosts to save facts without being asked, and no prompt-injection guidance was found", "The cloud terms of 20 January 2026 forbid automated extraction and allow discontinuing the service without notice", "Several outside bug reports, such as a silent capture failure, have no reply" ], "agentNotes": [ "Write new code against `/api/v2`; `/api/v1` is a legacy alias that may go in a future major release", "Call `/api/v2/memory/flush` at the end of a session, since `add` is asynchronous and buffers recent messages", "Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written", "Keep `host` at 127.0.0.1 unless something in front adds authentication", "Treat recalled memories as untrusted text, since they are extracted from past conversations" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.4 } ], "editorialScores": { "ergonomics": 78, "maintenance": 80, "payments": 40, "reliability": 79, "schema": 89, "security": 47, "transparency": 66 }, "provenanceScore": 75, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "uv pip install everos \u0026\u0026 everos init \u0026\u0026 everos server start", "http": "curl http://127.0.0.1:8000/health", "claudeCode": "claude mcp add everos -e EVEROS_BASE_URL=http://127.0.0.1:8000 -- uvx everos-mcp" }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/everos" }, "area": "agent-runtime", "provenance": { "legalEntity": "Evermind AI, Inc.", "domain": "evermind.ai", "domainRegistered": "2020-02-22", "endpointOnVendorDomain": null, "terms": "https://evermind.ai/terms-of-service", "privacy": "https://evermind.ai/privacy-policy", "statusPage": "", "changelog": "https://github.com/EverMind-AI/EverOS/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "Terms and privacy policy both say last updated 20 January 2026 and name Evermind AI, Inc. The terms choose Singapore law and forbid extracting data by bots, scripts, crawlers or data-mining tools, recorded here as a fact.", "evermind.ai/robots.txt allows all crawlers and names Claude-Web and anthropic-ai as allowed. docs.evermind.ai carries Content-Signal ai-input=yes.", "RDAP gives evermind.ai a registration date of 22 February 2020.", "security.txt at evermind.ai/.well-known/ gives contact@evermind.ai and a policy URL, expiring 28 February 2027.", "The about page is drawn by script and returned no readable text." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/everos.json", "live": { "slug": "everos", "versions": [ { "registry": "github", "name": "EverMind-AI/EverOS", "version": "v1.5.1", "released": "2026-10-22", "seenAt": "2026-11-06T23:24:44.540703115Z" }, { "registry": "pypi", "name": "everos", "version": "1.5.1", "released": "2026-10-22", "seenAt": "2026-11-06T23:24:41.488069905Z" }, { "registry": "pypi", "name": "everos-mcp", "version": "0.1.1", "released": "2026-10-15", "seenAt": "2026-11-06T23:24:42.65503941Z" } ], "githubStars": 13840, "pypiWeekly": 4033, "securityTxt": { "url": "https://evermind.ai/.well-known/security.txt", "state": "valid", "expires": "2027-02-28T00:00:00Z", "checkedAt": "2026-11-07T16:01:32.419431813Z" }, "llmsTxt": { "url": "https://docs.evermind.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:26.933711899Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/EverMind-AI/EverOS/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:18:19.185692468Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "40ab92cf4d99" }, { "url": "https://evermind.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:09:24.819286526Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dcd843ca72fe" }, { "url": "https://evermind.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:09:28.72898661Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "009377ab61a3" } ], "updatedAt": "2026-11-07T16:01:32.419431813Z" } }, "answer": "EverOS scores 69.4 (B) on agent readiness against Honcho's 61.6 (C), and leads in 4 of 7 scored categories. Honcho leads on security \u0026 auth and payments \u0026 pricing.", "b": { "slug": "honcho", "name": "Honcho", "vendor": "Plastic Labs", "vendorUrl": "https://honcho.dev", "kind": "http-api", "category": "agent-memory", "summary": "Honcho is a memory API that models conversation participants, with integrations for Claude Code, Codex, Cursor, OpenCode, OpenClaw and Hermes. Its hosted MCP server is at mcp.honcho.dev.", "url": "https://www.anchorterminal.com/tools/honcho", "markdownUrl": "https://www.anchorterminal.com/tools/honcho.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/honcho.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/honcho.json", "dns": "honcho.grade.anchorterminal.com", "repo": "https://github.com/plastic-labs/honcho", "license": "AGPL-3.0", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.honcho.dev/v3", "packages": [ { "registry": "pypi", "name": "honcho-ai" }, { "registry": "npm", "name": "@honcho-ai/sdk" } ], "auth": "mixed", "authNotes": "Bearer API key (`hch-...`) on api.honcho.dev. The create-key endpoint mints further keys scoped to a workspace, peer or session, with an optional expiry, and they're revocable from the API Keys page. The hosted MCP at mcp.honcho.dev takes a key as a Bearer header or an OAuth token, plus an optional workspace header. The AgentCash endpoints take x402 or MPP payment instead of a key, with wallet sign-in for the free ones.", "pricing": "usage", "pricingNotes": "Ingestion (storage plus background reasoning) is $2.00 per million, and queries through `chat` cost $0.001 (minimal), $0.01 (low), $0.05 (medium), $0.10 (high) or $0.50 (max) each. Context retrieval is listed as unlimited. Startups that have raised under $5 million get $1,000 of credit and 12 months of subsidised pricing (https://honcho.dev/). New organisations get $100 of free credit (https://github.com/plastic-labs/honcho). Over x402 the ingestion price is $2 per million tokens of message content, with a $0.001 minimum and a $5.00 maximum per call (https://agentcash.honcho.dev/openapi.json).", "priceSummary": "$0.001 / call", "where": "hosted", "x402": { "level": "yes", "evidence": "An AgentCash storefront at agentcash.honcho.dev lists 16 POST endpoints under /api/honcho/. Storing messages and chat are paid over x402 or Tempo MPP on Base, Solana or Tempo. Messages cost $2 per million tokens (minimum $0.001, maximum $5.00), chat $0.001 to $0.50 by reasoning level, and the other endpoints are free (https://agentcash.honcho.dev/openapi.json, checked 2026-09-30).", "endpoints": [ { "url": "https://agentcash.honcho.dev/api/honcho/messages", "priceUsd": 0.001, "network": "eip155:8453" }, { "url": "https://agentcash.honcho.dev/api/honcho/chat", "priceUsd": 0.001, "network": "eip155:8453" } ] }, "toolCount": 40, "popularity": { "githubStars": 7400, "npmWeekly": 17913, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://honcho.dev/docs", "llmsTxt": "https://honcho.dev/docs/llms.txt", "openapi": "https://honcho.dev/docs/v3/openapi.json", "registryName": "io.github.plastic-labs/honcho", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "tags": [ "hosted", "usage-priced", "x402", "stablecoin", "mcp", "oauth", "llms-txt", "python", "typescript", "open-source", "self-hosted" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 61.6, "grade": "C", "agentReady": false, "rank": 603, "ranked": true, "rankOf": 1510, "categoryRank": 9, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 71, "maintenance": 83, "payments": 80, "reliability": 50, "schema": 84, "security": 52, "transparency": 69 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": -6, "negativeNotes": [ "-3: v3.5.0 and SDK 2.8.0 (2026-10-29, minor releases) changed workspace configuration updates from merging to replacing the stored object, so a client sending one setting now clears the rest. The changelog announced it the day it shipped, with no earlier notice found (https://github.com/plastic-labs/honcho/blob/main/CHANGELOG.md, https://honcho.dev/docs/changelog/introduction)", "-3: released fixes with no advisory. v3.2.0 (2026-09-15) stopped peer-scoped keys reaching sessions and peers outside their scope on POST /sessions and POST /peers, and v3.3.0 (2026-10-09) stopped session clones copying a same-named session's data from another workspace. No advisory found in OSV or the commits (https://github.com/plastic-labs/honcho/blob/main/CHANGELOG.md)" ], "verdict": "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.", "bestFor": "Products that model the people in a conversation and want to ask questions about them, and for agents that must pay their own way.", "strengths": [ "Pay per call over x402 or MPP at agentcash.honcho.dev, with free read endpoints", "Keys can be minted per workspace, peer or session, with an expiry, through the API", "Context retrieval listed as unlimited, with reasoning billed only when you call chat", "Hosted MCP in the official registry with 40 annotated tools, plus OpenAPI specs for v1 to v3", "AGPL-3.0 server, the same code that runs the hosted service" ], "weaknesses": [ "No published rate limits, 429 guidance or SLA", "v3.5.0 changed workspace configuration updates from merge to replace with no advance notice", "Access-control fixes in v3.2.0 and v3.3.0 shipped without an advisory", "No security.txt, audit log or prompt-injection guidance found", "AGPL-3.0 server licence" ], "agentNotes": [ "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", "Batch up to 100 messages per request, each under 25,000 characters", "Use context retrieval for routine turns and save `chat` at high or max for questions that need it, since max costs 500 times minimal", "Mint a peer- or session-scoped key with an expiry for any agent that shouldn't see the whole workspace", "Over x402, batch messages rather than sending them singly, as each paid call has a $0.001 floor" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.6 } ], "editorialScores": { "ergonomics": 71, "maintenance": 83, "payments": 80, "reliability": 50, "schema": 84, "security": 52, "transparency": 56 }, "provenanceScore": 81, "checked": { "categories": { "ergonomics": "2026-11-02", "maintenance": "2026-11-02", "payments": "2026-11-02", "reliability": "2026-11-02", "schema": "2026-11-02", "security": "2026-11-02", "transparency": "2026-11-02" }, "last": "2026-11-02", "lastMoved": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install honcho-ai # or: npm install @honcho-ai/sdk", "http": "curl -X POST https://api.honcho.dev/v3/workspaces -H \"Authorization: Bearer $HONCHO_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"id\":\"workspace-123\",\"metadata\":{}}'", "claudeCode": "claude mcp add honcho --transport http \"https://mcp.honcho.dev\" --header \"Authorization: Bearer $HONCHO_API_KEY\"", "config": { "mcpServers": { "honcho": { "headers": { "Authorization": "Bearer ${HONCHO_API_KEY}" }, "type": "http", "url": "https://mcp.honcho.dev" } } }, "x402": "curl -s -i -X POST https://agentcash.honcho.dev/api/honcho/messages -H 'content-type: application/json'\n# 402 -\u003e pay over x402 (USDC on eip155:8453, or Solana) or Tempo MPP -\u003e retry. Request schemas at https://agentcash.honcho.dev/openapi.json" }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/honcho" }, "area": "agent-runtime", "unitPrices": [ { "item": "Ingestion", "unit": "1m-tokens", "usd": 2, "note": "Storage plus background reasoning. $0.001 minimum per call over x402" }, { "item": "chat, minimal reasoning", "unit": "call", "usd": 0.001 }, { "item": "chat, low reasoning", "unit": "call", "usd": 0.01 }, { "item": "chat, medium reasoning", "unit": "call", "usd": 0.05 }, { "item": "chat, high reasoning", "unit": "call", "usd": 0.1 }, { "item": "chat, max reasoning", "unit": "call", "usd": 0.5 } ], "provenance": { "legalEntity": "Plastic Labs, Inc.", "domain": "honcho.dev", "domainRegistered": "2022-01-26", "endpointOnVendorDomain": true, "terms": "https://app.honcho.dev/tos", "privacy": "https://app.honcho.dev/privacy", "statusPage": "https://status.honcho.dev", "changelog": "https://honcho.dev/docs/changelog/introduction", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The terms name Plastic Labs, Inc., 169 Madison Avenue, New York, with arbitration in New York. They carry no last-updated date.", "honcho.dev/.well-known/security.txt returns 404.", "The x402 storefront runs on the AgentCash platform at agentcash.honcho.dev, a subdomain of honcho.dev." ], "score": 81 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/honcho.json", "live": { "slug": "honcho", "probe": { "target": "https://api.honcho.dev/v3", "method": "get", "lastAt": "2026-11-07T19:22:11.903179679Z", "lastOk": true, "lastStatus": 401, "lastMs": 142, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 175, "p95ms24h": 456, "samples24h": 238, "samples30d": 7920, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.honcho.dev", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:22:15.342934653Z" }, "versions": [ { "registry": "github", "name": "plastic-labs/honcho", "version": "v3.5.0", "released": "2026-10-30", "seenAt": "2026-11-06T23:33:00.861976661Z" }, { "registry": "mcp-registry", "name": "io.github.plastic-labs/honcho", "version": "3.0.0", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "@honcho-ai/sdk", "version": "2.8.0", "seenAt": "2026-11-06T23:33:00.622074981Z" }, { "registry": "pypi", "name": "honcho-ai", "version": "2.8.0", "released": "2026-10-30", "seenAt": "2026-11-06T23:33:00.413883848Z" } ], "githubStars": 7985, "npmWeekly": 33764, "pypiWeekly": 67465, "securityTxt": { "url": "https://honcho.dev/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:08.247174915Z" }, "llmsTxt": { "url": "https://honcho.dev/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:42.419602302Z" }, "domain": { "domain": "honcho.dev", "registered": "2022-01-26", "source": "https://pubapi.registry.google/rdap/domain/honcho.dev", "checkedAt": "2026-11-01T14:18:34.31702211Z" }, "pages": [ { "url": "https://honcho.dev/docs/changelog/introduction", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:11:08.348330602Z", "changedAt": "2026-11-06T13:33:12.598540414Z", "fingerprint": "60f2494ff6a8" }, { "url": "https://app.honcho.dev/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T13:59:26.250943957Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9da63f6bcbbd" }, { "url": "https://app.honcho.dev/tos", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T13:59:28.445165354Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "f178ff16d893" } ], "mcpTools": { "url": "https://mcp.honcho.dev", "checkedAt": "2026-11-07T01:45:19.776240872Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:45:19.776240872Z" }, "github": { "repo": "plastic-labs/honcho", "checkedAt": "2026-11-02T09:17:29.930933158Z", "stars": 7887, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-01T20:47:02Z", "openIssues": 103, "openPRs": 72, "issuesOpened90d": 135, "issuesClosed90d": 119, "prsMerged90d": 307, "ci": { "branch": "main", "runs": 50, "success": 42, "failure": 6, "other": 2, "latest": "success", "latestAt": "2026-10-30T19:10:32Z" }, "replies": { "sampled": 25, "unanswered": 14, "medianDays": 1.2 } }, "updatedAt": "2026-11-07T19:22:11.903179679Z" } }, "edges": [ { "by": 40, "category": "payments", "leads": "honcho", "name": "Payments \u0026 pricing", "reasons": { "a": "Self-hosted rule, with the price lines read for EverOS Cloud. No x402, MPP or L402 (0 of 40). No cloud price or plan found on evermind.ai, its FAQ, terms or docs (0). The open-source runtime is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 40.", "b": "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)." }, "scores": { "a": 40, "b": 80 } }, { "by": 29, "category": "reliability", "leads": "everos", "name": "Reliability", "reasons": { "a": "Local-software lines, as a library and server the owner runs. `everos` on PyPI with Python 3.12 or newer stated, plus a Windows guide (20). ci.yml runs on pushes and pull requests and the repository has a tests tree, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 43 open issues and pull requests against 82 commits in 90 days; several outside bug reports, including a silent capture failure in the DSH plugin, have no reply (14 of 25). Keep a Changelog with semantic versioning declared and a 1.0 migration guide (15). Version 1.5.1 (15). Total 79.", "b": "Rootly status page at status.honcho.dev with Honcho API and Web Dashboard components and history (20). Per the 1 October check, the window holds slow provisioning of new instances on 17 August (about 7 hours, existing instances unaffected) and 36 minutes of migration downtime on 17 September, minor only (20). status.honcho.dev answered a Cloudflare bot check on 2 November, so 2 October to 2 November is unread and isn't credited. No published rate limits found; a Gmail import guide mentions Honcho's rate limits without numbers (0). No 429 or retry guidance found (0). No SLA found (0). The v3 API is generally available (10)." }, "scores": { "a": 79, "b": 50 } }, { "by": 7, "category": "ergonomics", "leads": "everos", "name": "Agent ergonomics", "reasons": { "a": "Read for the API, with seven MCP tools on top. Searches take `top_k` and a method, and responses can be scoped by five ids (20 of 25). Filters nest with AND and OR, and `/get` pages results (18 of 20). Errors carry typed codes and say which are retryable (16 of 20). `add` is queued and returns 202, a busy session refuses deletion with nothing deleted, and the cloud purge needs a nonce confirmed within five minutes (12 of 20). A demo runs with no key and the minimal setup needs one OpenRouter key, with a Python library and the MCP server, one language (12 of 15). Total 78.", "b": "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)." }, "scores": { "a": 78, "b": 71 } }, { "by": 5, "category": "schema", "leads": "everos", "name": "Schema \u0026 documentation", "reasons": { "a": "OpenAPI document in the repository with 40 operations, every one with a description (25). llms.txt and llms-full.txt on docs.evermind.ai (10). Operation descriptions state purpose; when-not-to-use guidance appears in the docs, such as flush after add, rather than per operation (15 of 20). Typed request models with filter operators eq, ne, gt, gte, lt, lte and in, and 422 on malformed ids (12 of 15). curl examples for add, flush and search, and typed error codes such as SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE (12 of 15). `/api/v2` with `/api/v1` kept as a legacy alias, a changelog and release notes (15). Total 89.", "b": "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)." }, "scores": { "a": 89, "b": 84 } }, { "by": 5, "category": "security", "leads": "honcho", "name": "Security \u0026 auth", "reasons": { "a": "Framework reading for software the owner runs. The local server has no authentication and no security scheme in the OpenAPI document, relying on a 127.0.0.1 bind by default (15 of 30). No read-only mode; the cloud purge is two-step (8 of 20). Memories are extracted from conversations and returned into prompts, and everos-mcp tells hosts to save facts unprompted, with no injection guidance found (4 of 15). Structured logs and lock metrics, no audit log (6 of 15). SECURITY.md with a reporting address, five-day acknowledgement, supported versions and a published-advisories section, plus a valid security.txt (14 of 20). Total 47.", "b": "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)." }, "scores": { "a": 47, "b": 52 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Evermind AI, Inc.", "b": "Plastic Labs", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.honcho.dev/v3", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "yes, from $0.001/call", "name": "x402" }, { "a": "Apache-2.0", "b": "AGPL-3.0", "name": "Licence" }, { "a": "7", "b": "40", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "io.github.plastic-labs/honcho", "name": "MCP registry" }, { "a": "2026-10-22", "b": "2026-10-29", "name": "Last release" }, { "a": "2026-01-20", "b": "no date given", "name": "Terms last updated" }, { "a": "2026-01-20", "b": "2025-04-24", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "14k stars, 4k PyPI/wk", "b": "7.4k stars, 18k npm/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "EverOS scores 69.4 (B) on agent readiness against Honcho's 61.6 (C), and leads in 4 of 7 scored categories. Honcho leads on security \u0026 auth and payments \u0026 pricing.", "question": "Which is better for AI agents, EverOS or Honcho?" }, { "answer": "EverOS needs no key. Honcho takes an API key or an OAuth sign-in. An agent can also pay Honcho per call over x402, with no account.", "question": "Do EverOS and Honcho need an API key?" }, { "answer": "EverOS runs on your own machine, with no hosted endpoint listed. Honcho has a hosted endpoint at https://api.honcho.dev/v3.", "question": "Can an agent call EverOS and Honcho without installing anything?" }, { "answer": "Yes. EverOS is open source (Apache-2.0). Honcho is open source (AGPL-3.0).", "question": "Are EverOS and Honcho open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 79 against 50", "Schema \u0026 documentation, 89 against 84", "Agent ergonomics, 78 against 71" ], "also": [ "No key needed to call it", "Runs on your own machine", "No incidents deducted, where Honcho loses 6 points for them" ], "goodFor": "Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.", "slug": "everos", "watchFor": "The local HTTP server has no authentication and relies on binding to 127.0.0.1" }, { "aheadOn": [ "Security \u0026 auth, 52 against 47", "Payments \u0026 pricing, 80 against 40" ], "also": [ "An agent can pay per call over x402, with no account", "A hosted endpoint, with nothing to install" ], "goodFor": "Products that model the people in a conversation and want to ask questions about them, and for agents that must pay their own way.", "slug": "honcho", "watchFor": "No published rate limits, 429 guidance or SLA" } ], "history": { "everos": null, "honcho": [ { "causes": [ "evidence", "event" ], "date": "2026-11-02", "delta": -2.6, "from": 64.2, "fromGrade": "B", "to": 61.6, "toGrade": "C" }, { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0.1, "from": 64.1, "fromGrade": "B", "to": 64.2, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0, "from": 64.1, "fromGrade": "B", "to": 64.1, "toGrade": "B" } ] }, "job": { "capability": "memory.store", "name": "Agent memory" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-everos.json", "title": "Amazon Bedrock AgentCore Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-honcho.json", "title": "Amazon Bedrock AgentCore Memory vs Honcho", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/basic-memory-vs-everos.json", "title": "Basic Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/basic-memory-vs-honcho.json", "title": "Basic Memory vs Honcho", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-everos.json", "title": "claude-mem vs EverOS", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-honcho.json", "title": "claude-mem vs Honcho", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-everos.json", "title": "Cognee vs EverOS", "url": "https://www.anchorterminal.com/compare/cognee-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-honcho.json", "title": "Cognee vs Honcho", "url": "https://www.anchorterminal.com/compare/cognee-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.json", "title": "EverOS vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/everos-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-graphicle.json", "title": "EverOS vs Graphicle", "url": "https://www.anchorterminal.com/compare/everos-vs-graphicle" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-graphiti.json", "title": "EverOS vs Graphiti", "url": "https://www.anchorterminal.com/compare/everos-vs-graphiti" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-hindsight.json", "title": "EverOS vs Hindsight", "url": "https://www.anchorterminal.com/compare/everos-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-hy-memory.json", "title": "EverOS vs Hy Memory", "url": "https://www.anchorterminal.com/compare/everos-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-langmem.json", "title": "EverOS vs LangMem", "url": "https://www.anchorterminal.com/compare/everos-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-localghost.json", "title": "EverOS vs LocalGhost", "url": "https://www.anchorterminal.com/compare/everos-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-mem0.json", "title": "EverOS vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/everos-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memmachine.json", "title": "EverOS vs MemMachine", "url": "https://www.anchorterminal.com/compare/everos-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memori.json", "title": "EverOS vs Memori", "url": "https://www.anchorterminal.com/compare/everos-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.json", "title": "EverOS vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-mempalace.json", "title": "EverOS vs MemPalace", "url": "https://www.anchorterminal.com/compare/everos-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-past-dev.json", "title": "EverOS vs past.dev", "url": "https://www.anchorterminal.com/compare/everos-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-supermemory.json", "title": "EverOS vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/everos-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.json", "title": "EverOS vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-tokenrip.json", "title": "EverOS vs Tokenrip", "url": "https://www.anchorterminal.com/compare/everos-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-zep.json", "title": "EverOS vs Zep", "url": "https://www.anchorterminal.com/compare/everos-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-honcho.json", "title": "Agent Platform Memory Bank vs Honcho", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-honcho.json", "title": "Graphiti vs Honcho", "url": "https://www.anchorterminal.com/compare/graphiti-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-honcho.json", "title": "Hindsight vs Honcho", "url": "https://www.anchorterminal.com/compare/hindsight-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-hy-memory.json", "title": "Honcho vs Hy Memory", "url": "https://www.anchorterminal.com/compare/honcho-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-langmem.json", "title": "Honcho vs LangMem", "url": "https://www.anchorterminal.com/compare/honcho-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-localghost.json", "title": "Honcho vs LocalGhost", "url": "https://www.anchorterminal.com/compare/honcho-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-mem0.json", "title": "Honcho vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/honcho-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-memmachine.json", "title": "Honcho vs MemMachine", "url": "https://www.anchorterminal.com/compare/honcho-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-memori.json", "title": "Honcho vs Memori", "url": "https://www.anchorterminal.com/compare/honcho-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.json", "title": "Honcho vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-mempalace.json", "title": "Honcho vs MemPalace", "url": "https://www.anchorterminal.com/compare/honcho-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-past-dev.json", "title": "Honcho vs past.dev", "url": "https://www.anchorterminal.com/compare/honcho-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-supermemory.json", "title": "Honcho vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/honcho-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-tencentdb-agent-memory.json", "title": "Honcho vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/honcho-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-tokenrip.json", "title": "Honcho vs Tokenrip", "url": "https://www.anchorterminal.com/compare/honcho-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-zep.json", "title": "Honcho vs Zep", "url": "https://www.anchorterminal.com/compare/honcho-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-everos.json", "title": "AI Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-honcho.json", "title": "AI Memory vs Honcho", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-everos.json", "title": "Context Mode Engine vs EverOS", "url": "https://www.anchorterminal.com/compare/context-mode-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-honcho.json", "title": "Context Mode Engine vs Honcho", "url": "https://www.anchorterminal.com/compare/context-mode-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/graphicle-vs-honcho.json", "title": "Graphicle vs Honcho", "url": "https://www.anchorterminal.com/compare/graphicle-vs-honcho" } ], "panel": null, "scores": [ { "by": 29, "edge": "everos", "everos": 79, "honcho": 50, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 5, "edge": "everos", "everos": 89, "honcho": 84, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 7, "edge": "everos", "everos": 78, "honcho": 71, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 5, "edge": "honcho", "everos": 47, "honcho": 52, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 40, "edge": "honcho", "everos": 40, "honcho": 80, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 3, "edge": "honcho", "everos": 80, "honcho": 83, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 2, "edge": "everos", "everos": 71, "honcho": 69, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "EverOS scores 69.4 (B) on agent readiness against Honcho's 61.6 (C), and leads in 4 of 7 scored categories. Honcho leads on security \u0026 auth and payments \u0026 pricing. Both do agent memory. Honcho accepts x402. EverOS doesn't.", "tasks": null, "tutorials": [], "verdicts": { "everos": "EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/everos-vs-honcho", "json": "https://www.anchorterminal.com/compare/everos-vs-honcho.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/everos-vs-honcho.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/everos-vs-honcho.min.md" }, "markdown": "EverOS scores 69.4 (B) on agent readiness against Honcho's 61.6 (C), and leads in 4 of 7 scored categories. Honcho leads on security \u0026 auth and payments \u0026 pricing. Both do agent memory. Honcho accepts x402. EverOS doesn't.\n\n- EverOS: grade B, 69.4/100, rank #247 of 1510. Markdown https://www.anchorterminal.com/tools/everos.md · JSON https://www.anchorterminal.com/api/v1/tools/everos.json\n- Honcho: grade C, 61.6/100, rank #603 of 1510. Markdown https://www.anchorterminal.com/tools/honcho.md · JSON https://www.anchorterminal.com/api/v1/tools/honcho.json\n- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 353 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n\n## Which one, for what\n\n### EverOS (B)\n\nGood for: Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.\n\nAhead on:\n- Reliability, 79 against 50\n- Schema \u0026 documentation, 89 against 84\n- Agent ergonomics, 78 against 71\n\nAlso in its favour:\n- No key needed to call it\n- Runs on your own machine\n- No incidents deducted, where Honcho loses 6 points for them\n\nWatch for: The local HTTP server has no authentication and relies on binding to 127.0.0.1\n\n### Honcho (C)\n\nGood 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.\n\nAhead on:\n- Security \u0026 auth, 52 against 47\n- Payments \u0026 pricing, 80 against 40\n\nAlso in its favour:\n- An agent can pay per call over x402, with no account\n- A hosted endpoint, with nothing to install\n\nWatch for: No published rate limits, 429 guidance or SLA\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Honcho +40\n\n- EverOS (40): Self-hosted rule, with the price lines read for EverOS Cloud. No x402, MPP or L402 (0 of 40). No cloud price or plan found on evermind.ai, its FAQ, terms or docs (0). The open-source runtime is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 40.\n- Honcho (80): 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).\n\n### Reliability: EverOS +29\n\n- EverOS (79): Local-software lines, as a library and server the owner runs. `everos` on PyPI with Python 3.12 or newer stated, plus a Windows guide (20). ci.yml runs on pushes and pull requests and the repository has a tests tree, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 43 open issues and pull requests against 82 commits in 90 days; several outside bug reports, including a silent capture failure in the DSH plugin, have no reply (14 of 25). Keep a Changelog with semantic versioning declared and a 1.0 migration guide (15). Version 1.5.1 (15). Total 79.\n- Honcho (50): Rootly status page at status.honcho.dev with Honcho API and Web Dashboard components and history (20). Per the 1 October check, the window holds slow provisioning of new instances on 17 August (about 7 hours, existing instances unaffected) and 36 minutes of migration downtime on 17 September, minor only (20). status.honcho.dev answered a Cloudflare bot check on 2 November, so 2 October to 2 November is unread and isn't credited. No published rate limits found; a Gmail import guide mentions Honcho's rate limits without numbers (0). No 429 or retry guidance found (0). No SLA found (0). The v3 API is generally available (10).\n\n### Agent ergonomics: EverOS +7\n\n- EverOS (78): Read for the API, with seven MCP tools on top. Searches take `top_k` and a method, and responses can be scoped by five ids (20 of 25). Filters nest with AND and OR, and `/get` pages results (18 of 20). Errors carry typed codes and say which are retryable (16 of 20). `add` is queued and returns 202, a busy session refuses deletion with nothing deleted, and the cloud purge needs a nonce confirmed within five minutes (12 of 20). A demo runs with no key and the minimal setup needs one OpenRouter key, with a Python library and the MCP server, one language (12 of 15). Total 78.\n- 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).\n\n### Schema \u0026 documentation: EverOS +5\n\n- EverOS (89): OpenAPI document in the repository with 40 operations, every one with a description (25). llms.txt and llms-full.txt on docs.evermind.ai (10). Operation descriptions state purpose; when-not-to-use guidance appears in the docs, such as flush after add, rather than per operation (15 of 20). Typed request models with filter operators eq, ne, gt, gte, lt, lte and in, and 422 on malformed ids (12 of 15). curl examples for add, flush and search, and typed error codes such as SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE (12 of 15). `/api/v2` with `/api/v1` kept as a legacy alias, a changelog and release notes (15). Total 89.\n- 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).\n\n### Security \u0026 auth: Honcho +5\n\n- EverOS (47): Framework reading for software the owner runs. The local server has no authentication and no security scheme in the OpenAPI document, relying on a 127.0.0.1 bind by default (15 of 30). No read-only mode; the cloud purge is two-step (8 of 20). Memories are extracted from conversations and returned into prompts, and everos-mcp tells hosts to save facts unprompted, with no injection guidance found (4 of 15). Structured logs and lock metrics, no audit log (6 of 15). SECURITY.md with a reporting address, five-day acknowledgement, supported versions and a published-advisories section, plus a valid security.txt (14 of 20). Total 47.\n- 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).\n\n## Score by category\n\n| Category | Weight | EverOS | Honcho | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 79 | 50 | EverOS +29 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 89 | 84 | EverOS +5 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 71 | EverOS +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 47 | 52 | Honcho +5 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 80 | Honcho +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 83 | Honcho +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 71 | 69 | EverOS +2 |\n| Negative events | ≤15 | 0 | -6 | |\n| **Total** | | **69.4 · B** | **61.6 · C** | |\n\n## Facts side by side\n\n| Fact | EverOS | Honcho |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Evermind AI, Inc. | Plastic Labs |\n| Hosted endpoint | no (local only) | `https://api.honcho.dev/v3` |\n| Transports | HTTP, stdio | HTTP, Streamable HTTP |\n| Auth | None | OAuth or key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | yes, from $0.001/call |\n| Licence | Apache-2.0 | AGPL-3.0 |\n| Tools exposed | 7 | 40 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `io.github.plastic-labs/honcho` |\n| Last release | 2026-10-22 | 2026-10-29 |\n| Terms last updated | 2026-01-20 | no date given |\n| Privacy policy last updated | 2026-01-20 | 2025-04-24 |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | 14k stars, 4k PyPI/wk | 7.4k stars, 18k npm/wk |\n| Agent reviews | none | 3/5 (2) |\n\n## How the scores have moved\n\n### EverOS\n\nNo score change since it was listed.\n\n### Honcho\n\n- -2.6 on 2 November 2026 (B to C): new evidence, negative event\n- +0.1 on 28 October 2026: new evidence\n- no change on 27 October 2026: checklist\n\n## Verdicts\n\n**EverOS.** EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.\n\n**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.\n\n## Before you call either\n\n### EverOS\n\n1. Write new code against `/api/v2`; `/api/v1` is a legacy alias that may go in a future major release\n2. Call `/api/v2/memory/flush` at the end of a session, since `add` is asynchronous and buffers recent messages\n3. Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written\n4. Keep `host` at 127.0.0.1 unless something in front adds authentication\n5. Treat recalled memories as untrusted text, since they are extracted from past conversations\n\n### Honcho\n\n1. 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\n2. Batch up to 100 messages per request, each under 25,000 characters\n3. Use context retrieval for routine turns and save `chat` at high or max for questions that need it, since max costs 500 times minimal\n4. Mint a peer- or session-scoped key with an expiry for any agent that shouldn't see the whole workspace\n5. Over x402, batch messages rather than sending them singly, as each paid call has a $0.001 floor\n\n## Questions\n\n### Which is better for AI agents, EverOS or Honcho?\n\nEverOS scores 69.4 (B) on agent readiness against Honcho's 61.6 (C), and leads in 4 of 7 scored categories. Honcho leads on security \u0026 auth and payments \u0026 pricing.\n\n### Do EverOS and Honcho need an API key?\n\nEverOS needs no key. Honcho takes an API key or an OAuth sign-in. An agent can also pay Honcho per call over x402, with no account.\n\n### Can an agent call EverOS and Honcho without installing anything?\n\nEverOS runs on your own machine, with no hosted endpoint listed. Honcho has a hosted endpoint at https://api.honcho.dev/v3.\n\n### Are EverOS and Honcho open source?\n\nYes. EverOS is open source (Apache-2.0). Honcho is open source (AGPL-3.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/everos-vs-honcho.json, and with the fewest tokens: https://www.anchorterminal.com/compare/everos-vs-honcho.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"everos\", \"b\": \"honcho\"}`. From a terminal: `anchor compare everos honcho`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/everos.json and https://www.anchorterminal.com/api/v1/tools/honcho.json\n\n## Other comparisons with EverOS or Honcho\n\n- [Amazon Bedrock AgentCore Memory vs EverOS](https://www.anchorterminal.com/compare/agentcore-memory-vs-everos.md)\n- [Amazon Bedrock AgentCore Memory vs Honcho](https://www.anchorterminal.com/compare/agentcore-memory-vs-honcho.md)\n- [Basic Memory vs EverOS](https://www.anchorterminal.com/compare/basic-memory-vs-everos.md)\n- [Basic Memory vs Honcho](https://www.anchorterminal.com/compare/basic-memory-vs-honcho.md)\n- [claude-mem vs EverOS](https://www.anchorterminal.com/compare/claude-mem-vs-everos.md)\n- [claude-mem vs Honcho](https://www.anchorterminal.com/compare/claude-mem-vs-honcho.md)\n- [Cognee vs EverOS](https://www.anchorterminal.com/compare/cognee-vs-everos.md)\n- [Cognee vs Honcho](https://www.anchorterminal.com/compare/cognee-vs-honcho.md)\n- [EverOS vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.md)\n- [EverOS vs Graphicle](https://www.anchorterminal.com/compare/everos-vs-graphicle.md)\n- [EverOS vs Graphiti](https://www.anchorterminal.com/compare/everos-vs-graphiti.md)\n- [EverOS vs Hindsight](https://www.anchorterminal.com/compare/everos-vs-hindsight.md)\n- [EverOS vs Hy Memory](https://www.anchorterminal.com/compare/everos-vs-hy-memory.md)\n- [EverOS vs LangMem](https://www.anchorterminal.com/compare/everos-vs-langmem.md)\n- [EverOS vs LocalGhost](https://www.anchorterminal.com/compare/everos-vs-localghost.md)\n- [EverOS vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/everos-vs-mem0.md)\n- [EverOS vs MemMachine](https://www.anchorterminal.com/compare/everos-vs-memmachine.md)\n- [EverOS vs Memori](https://www.anchorterminal.com/compare/everos-vs-memori.md)\n- [EverOS vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.md)\n- [EverOS vs MemPalace](https://www.anchorterminal.com/compare/everos-vs-mempalace.md)\n- [EverOS vs past.dev](https://www.anchorterminal.com/compare/everos-vs-past-dev.md)\n- [EverOS vs Supermemory API + MCP](https://www.anchorterminal.com/compare/everos-vs-supermemory.md)\n- [EverOS vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.md)\n- [EverOS vs Tokenrip](https://www.anchorterminal.com/compare/everos-vs-tokenrip.md)\n- [EverOS vs Zep](https://www.anchorterminal.com/compare/everos-vs-zep.md)\n- [Agent Platform Memory Bank vs Honcho](https://www.anchorterminal.com/compare/google-memory-bank-vs-honcho.md)\n- [Graphiti vs Honcho](https://www.anchorterminal.com/compare/graphiti-vs-honcho.md)\n- [Hindsight vs Honcho](https://www.anchorterminal.com/compare/hindsight-vs-honcho.md)\n- [Honcho vs Hy Memory](https://www.anchorterminal.com/compare/honcho-vs-hy-memory.md)\n- [Honcho vs LangMem](https://www.anchorterminal.com/compare/honcho-vs-langmem.md)\n- [Honcho vs LocalGhost](https://www.anchorterminal.com/compare/honcho-vs-localghost.md)\n- [Honcho vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/honcho-vs-mem0.md)\n- [Honcho vs MemMachine](https://www.anchorterminal.com/compare/honcho-vs-memmachine.md)\n- [Honcho vs Memori](https://www.anchorterminal.com/compare/honcho-vs-memori.md)\n- [Honcho vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.md)\n- [Honcho vs MemPalace](https://www.anchorterminal.com/compare/honcho-vs-mempalace.md)\n- [Honcho vs past.dev](https://www.anchorterminal.com/compare/honcho-vs-past-dev.md)\n- [Honcho vs Supermemory API + MCP](https://www.anchorterminal.com/compare/honcho-vs-supermemory.md)\n- [Honcho vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/honcho-vs-tencentdb-agent-memory.md)\n- [Honcho vs Tokenrip](https://www.anchorterminal.com/compare/honcho-vs-tokenrip.md)\n- [Honcho vs Zep](https://www.anchorterminal.com/compare/honcho-vs-zep.md)\n- [AI Memory vs EverOS](https://www.anchorterminal.com/compare/ai-memory-vs-everos.md)\n- [AI Memory vs Honcho](https://www.anchorterminal.com/compare/ai-memory-vs-honcho.md)\n- [Context Mode Engine vs EverOS](https://www.anchorterminal.com/compare/context-mode-vs-everos.md)\n- [Context Mode Engine vs Honcho](https://www.anchorterminal.com/compare/context-mode-vs-honcho.md)\n- [Graphicle vs Honcho](https://www.anchorterminal.com/compare/graphicle-vs-honcho.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "EverOS vs Honcho", "url": "" } ], "description": "EverOS scores 69.4 (B) to Honcho's 61.6 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "EverOS B 69.4", "Honcho C 61.6", "scores" ], "h1": "EverOS vs Honcho", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/everos-vs-honcho", "published": "2026-10-01", "section": "tools", "title": "EverOS vs Honcho for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/everos-vs-honcho" }, "tokens": { "markdown": 4500, "slim": 2280 }, "version": 1 }