mirror of
https://github.com/rohitg00/agentmemory.git
synced 2026-09-14 20:16:33 +08:00
v0.9.19
19 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Rohit Ghumare
|
00df540c87 |
fix(fs-watcher): redact PEM private-key blocks and standalone JWTs in previews (#448) (#450)
PR #332 covered KEY=value and Bearer-prefixed tokens. This extends the filesystem watcher's preview pipeline to also collapse multi-line and inline PEM private-key blocks (RSA / DSA / EC / OPENSSH / ENCRYPTED / generic) into a single REDACTED line bracketed by the BEGIN/END markers, and to redact standalone JWT-looking strings outside Bearer context. JWT redaction requires a three-segment dot pattern AND total length >= 100 chars to avoid matching incidental base64-shaped words. Closes #448 |
||
|
이민재
|
e2f2217f59 |
fix: redact filesystem watcher previews before transport (#332)
* fix: redact filesystem watcher previews * fix: redact quoted sensitive preview keys --------- Co-authored-by: 이민재 <19909783+honor2030@users.noreply.github.com> |
||
|
Erwan Leboucher
|
1c8713f978 | fix(hermes): is_available() must not do network calls (#377) | ||
|
Virgile
|
57ffe91302 |
fix(hermes): use correct API keys tool_input/tool_output in sync_turn (#384)
The Hermes plugin's sync_turn() method sends conversation observations to the agentmemory /observe endpoint using keys 'input' and 'output', but the server's mem::observe handler extracts data using 'tool_input' and 'tool_output' (see src/functions/observe.ts). This key mismatch means raw.toolInput and raw.toolOutput are always undefined. When auto-compress is enabled, the LLM receives a nearly empty compression prompt (only timestamp + hookType + toolName), which produces generic, useless observations like: title: "Agent initiated conversation" narrative: "No specific content was provided" importance: 1 With the corrected keys, DeepSeek/Vision models receive the actual conversation content and produce meaningful, structured observations: title: "Verified fix for agentmemory plugin key naming" importance: 6 concepts: ["agentmemory plugin", "tool_input/tool_output key renaming"] facts: ["The fix replaces 'input'/'output' keys with..."] |
||
|
Matt Van Horn
|
1a706ca2d6 |
fix(integrations): warn when bearer auth crosses plaintext HTTP to non-loopback (#315)
* fix(integrations): warn when bearer auth crosses plaintext HTTP to non-loopback (#275) Signed-off-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com> * test(integrations/315): edge cases for IPv6 loopback + LAN IPs + lookalike hostnames + docs @mvanhorn's PR #315 lands the right plaintext-bearer-auth warn-once pattern across three runtimes (hermes/python, openclaw/mjs, pi/typescript). Reviewed cleanly. Adding test cases + docs before merge so the contract is locked: Test additions (test/integration-plaintext-http.test.ts pi suite, +4 cases, 13 total in suite): - IPv6 loopback (http://[::1]:3111) — URL parser strips brackets, hostname comes back as `::1`, the LOOPBACK_HOSTS set already covers this. Test pins the parsing semantic so a future refactor can't silently break it. - Private LAN IPs (RFC1918 ranges 192.168.x.y, 10.x.x.x) — NOT loopback, guard MUST warn. RFC1918 was a deliberate design choice (loopback set stays minimal: localhost / 127.0.0.1 / ::1). LAN deployment behind a tunnel still leaks the bearer over the wire. - No-secret short-circuit (guard with secret="" or undefined) — guard never fires when a bearer wouldn't actually be sent. Mirrors the usesPlaintextBearerAuth() early-return. - Lookalike hostname (http://localhost.evil.com:3111) — `parsed.hostname` returns the full `localhost.evil.com` string, which is NOT in LOOPBACK_HOSTS. Guard warns. This pins the exact-match (vs prefix) loopback semantic. Docs additions: - integrations/pi/README.md and integrations/hermes/README.md now document AGENTMEMORY_REQUIRE_HTTPS in the env-vars table — same row shape as AGENTMEMORY_SECRET, names the env value (=1), describes the warn-vs-throw semantic, and lists the loopback hostnames the guard recognises. No code changes to the guard itself — it's already correct. Pre-merge hardening only. 899 / 899 tests pass on rebased branch. Build clean. --------- Signed-off-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com> Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com> Co-authored-by: Rohit Ghumare <ghumare64@gmail.com> |
||
|
Rohit Ghumare
|
48b11e8351 |
fix(openclaw): claim plugins.slots.memory via registerMemoryCapability (#310)
* fix(openclaw): claim plugins.slots.memory via registerMemoryCapability
The OpenClaw integration declared kind: "memory" in its manifest and
wired before_agent_start / agent_end hooks, but never called
api.registerMemoryCapability(...). On OpenClaw 2026.4.9+ that
left plugins.slots.memory = "agentmemory" reporting unavailable
even though the hooks worked end-to-end and the REST API was
healthy.
Per OpenClaw's plugin SDK declarations
(plugin-sdk/src/plugins/types.d.ts), api.registerMemoryCapability
takes a MemoryPluginCapability and is the canonical way to occupy
the memory slot. All capability fields are optional. The
promptBuilder field has signature:
(params: { availableTools: Set<string>; citationsMode? }) => string[]
This commit:
- Calls api.registerMemoryCapability({ promptBuilder }) at register
time when the host exposes it. promptBuilder returns three lines
describing agentmemory as the active memory provider, including
the configured base_url so the agent knows where recall is
coming from.
- Guards on `typeof api.registerMemoryCapability === "function"`
so older OpenClaw builds (pre-capability API) still load via
the existing hook-only path. Net behaviour on older hosts is
unchanged.
- Does NOT register a runtime adapter. OpenClaw's current
MemoryRuntimeBackendConfig type is exactly { backend: "builtin" }
or { backend: "qmd"; qmd?: { command?: string } }; both are
in-process backends and don't fit an external REST service.
The hook-driven recall + capture flow is the working
integration path; runtime registration is documented as a
follow-up gated on an upstream OpenClaw change to add an
"external" backend variant.
README troubleshooting block adds a specific entry for the
"unavailable slot" symptom, pointing at the registerMemoryCapability
fix. The README also documents the runtime-adapter scope decision
so users running deep host integrations aren't surprised.
3 new tests in test/openclaw-plugin.test.ts assert:
1. registerMemoryCapability is called with a promptBuilder when
the host supports it.
2. Plugin still registers hooks and does not throw on older hosts
that don't expose registerMemoryCapability.
3. promptBuilder respects the configured base_url.
871 / 871 tests pass.
Verified against the openclaw npm package surface:
- api.registerMemoryCapability is declared at
plugin-sdk/src/plugins/types.d.ts:2028
- MemoryPluginCapability is declared at
plugin-sdk/src/plugins/memory-state.d.ts
- promptBuilder signature matches MemoryPromptSectionBuilder
- No import from openclaw/extensions/* needed (and that path is
not in the package's exports map anyway)
This is a fresh implementation. The closed PR #302 attempted the
same end goal but imported memoryRuntime from a non-existent
path (openclaw/extensions/memory-core/runtime-api) and would have
failed with ERR_PACKAGE_PATH_NOT_EXPORTED at load time.
* fix(openclaw): accept params arg in promptBuilder to match MemoryPromptSectionBuilder
Reviewer flagged that promptBuilder was declared as () => [...] which
doesn't match the MemoryPluginCapability contract verified from
openclaw@2026.5.7 (plugin-sdk/src/plugins/memory-state.d.ts):
type MemoryPromptSectionBuilder = (params: {
availableTools: Set<string>;
citationsMode?: MemoryCitationsMode;
}) => string[];
JavaScript would tolerate the zero-arg form at runtime (extra args
are ignored), but the signature was misleading and would fail a
TypeScript port. Updated to (_params) => [...] with a comment
explaining we accept-but-ignore. Underscore-prefix conveys
intentional non-use to lint/readers.
Validation: 3/3 openclaw tests still pass (they invoke
promptBuilder({ availableTools: new Set() }) — both old and new
signatures accept that call).
|
||
|
Rohit Ghumare
|
eaecc658d3 |
fix(hermes): serialize handle_tool_call returns to JSON string (closes #254) (#255)
Hermes stores handle_tool_call's return value as the tool result
`content` field in the session history. Anthropic-protocol LLM providers
reject non-string content on the next request with:
Failed to deserialize the JSON body into the target type:
messages[N]: content should be a string or a list at line 1 column XXXXX
Once triggered, every subsequent request in that session 400s until the
session JSON is manually cleaned.
The plugin's handle_tool_call returned raw Python dicts in all 4 paths
(memory_recall, memory_save, memory_search, unknown-tool fallback). Wrap
each return in json.dumps so the result is always a string.
This matches the contract that agentmemory's own MCP server already
honors in src/mcp/standalone.ts:
{ type: "text", text: JSON.stringify(payload, null, ...) }
Tightens the return-type annotation on both the abstract base and the
concrete class from Any -> str so mypy / type checkers catch any future
regression.
Reported by @KyoMio with full Anthropic-protocol repro.
|
||
|
Rohit Ghumare
|
c2f2618c74 |
fix(hermes): preload ~/.agentmemory/.env so status reflects service env (closes #250) (#253)
When agentmemory runs as a systemd user service (or any process manager that loads ~/.agentmemory/.env directly), the values never reach the shell that runs `hermes memory status`. Status then reads os.environ in the Hermes CLI process, finds AGENTMEMORY_URL / AGENTMEMORY_SECRET unset, and reports the plugin as "Missing" even though the service is healthy and live sessions can use it. Preload the documented config file at plugin-import time using os.environ.setdefault so anything explicitly set in the shell still wins. Best-effort: silently skip when the file is absent, unreadable, or malformed — the plugin falls back to its existing defaults. Both ~/.agentmemory/.env (primary, per agentmemory's own README) and $XDG_CONFIG_HOME/agentmemory/.env (fallback) are checked. Reported by @OptionalCoin. Tested: $ printf 'AGENTMEMORY_URL=http://example\nAGENTMEMORY_SECRET=s\n' \ > ~/.agentmemory/.env $ unset AGENTMEMORY_URL AGENTMEMORY_SECRET $ python -c "import sys; sys.path.insert(0, 'integrations'); \ import hermes; \ import os; \ print(os.environ['AGENTMEMORY_URL'])" http://example $ AGENTMEMORY_URL=http://shell-wins python -c "..." http://shell-wins # explicit shell value still wins |
||
|
Rohit Ghumare
|
2c24c9077e |
fix(hermes): accept passthrough kwargs in memory provider hooks (closes #249) (#252)
Hermes calls memory provider hooks with extra context kwargs (e.g. session_id) that the strict signatures rejected with: Memory provider 'agentmemory' sync_turn failed: AgentMemoryProvider. sync_turn() got an unexpected keyword argument 'session_id' Add **kwargs: Any to every hook so extra context fields are tolerated: sync_turn, on_session_end, on_pre_compress, on_memory_write, prefetch, queue_prefetch, shutdown. Mirror the same change on the abstract fallback MemoryProvider used when `agent.memory_provider` is unavailable at import time. Where Hermes passes session_id, prefer it over the cached self._session_id so per-turn observations land on the correct session when Hermes routes a hook through a different conversation than the one the provider was initialized with. Reported and locally verified by @OptionalCoin. |
||
|
Mandeep Singh
|
2daeb5afda | Add tested Pi/OpenClaw/Hermes integration fixes (#230) | ||
|
Rohit Ghumare
|
8f44c3ddde |
docs(hermes): correct plugin install path
Hermes scans `~/.hermes/plugins/<name>/` flat. Memory category namespace (`memory/`) is reserved for bundled providers and won't discover user plugins nested under it. Closes #197 |
||
|
Rohit Ghumare
|
02ebc5f1fa |
fix(fs-watcher): address CodeRabbit review
Three issues flagged by review. 1. CRITICAL - observe endpoint rejects current payload shape. The /agentmemory/observe handler requires a full HookPayload (non-empty hookType from the fixed HookType union, sessionId, project, cwd, timestamp) with observation data under 'data'. The watcher was emitting hookType='file_change'/'file_delete' (not valid HookType values), possibly-null sessionId and project, no cwd or timestamp, and files/content/metadata at the top level. The server would 400 every observation. Now emits hookType='post_tool_use' with changeKind moved into data.changeKind. sessionId auto-generates as fs-watcher-<ts>-<rand> when not supplied; project defaults to the first watched directory's basename. cwd is set to the root that triggered the event, timestamp to new Date().toISOString(). files/content/rootDir/absPath/size/truncated/source all sit under data. 2. MAJOR - start() returned successfully even when every fs.watch call failed. In CLI/supervisor usage that looked like a healthy start while no observations ever fired. Now start() throws if this.watchers ends up empty, with the node-version hint in the message since Node 18 + Linux is the likely cause. 3. MAJOR - engines.node was >=18, but fs.watch(recursive: true) on Linux only landed in Node 19.1.0. Raised to >=20 (next LTS after 19.x) and documented the requirement in README. test/fs-watcher.test.ts: - Updated two shape assertions (hookType, sessionId, project, cwd, timestamp at top level; files/content/changeKind under data). - Added test that start() throws when no roots can be watched. |
||
|
Rohit Ghumare
|
bfcff26cc1 |
feat: filesystem connector — emits observations on file changes (#62)
First of the data-source connectors tracked in #62. Ships as @agentmemory/fs-watcher under integrations/filesystem-watcher/. Scope (v0.1.0): - Watches one or more roots via node:fs.watch({recursive: true}). No native deps; works on macOS / Linux / Windows 10+. - Emits file_change / file_delete observations to POST /agentmemory/observe on the running server. - Debounces 500ms per path so a stream of editor saves collapses to a single observation. - Reads the first 4 KB of text files for content preview; truncation is flagged in metadata. Binary files are skipped by default (AGENTMEMORY_FS_WATCH_ALLOW_BINARY=1 to opt in). - Default ignore set: .git, node_modules, dist, build, .next, .turbo, coverage, .DS_Store, *.log, *.lock. Extensible via AGENTMEMORY_FS_WATCH_IGNORE. - Attaches Bearer AGENTMEMORY_SECRET when set. - CLI and env-driven config; CLI args win. Can be supervised with launchd / systemd / pm2. Tests (test/fs-watcher.test.ts): - file_change on write, file_delete on unlink. - Default ignore set skips node_modules/. - Bearer auth header attached when secret is configured. - Debounce collapses four rapid writes to <=2 observations. - configFromEnv parses dirs and regex ignore patterns. GitHub and Slack connectors (from #62) will be separate PRs since they need OAuth / token handling and a shared event-normalizer; the file-watcher has no such dependency and is useful standalone. |
||
|
Rohit Ghumare
|
416fa15af4 |
chore: release 0.8.6 — scope the MCP shim as @agentmemory/mcp (#134)
0.8.5's publish workflow got blocked on the unscoped `agentmemory-mcp` name by npm's name-similarity policy (there's an unrelated third-party package called `agent-memory-mcp`). Publishing the shim under the `@agentmemory` scope we already own sidesteps the conflict. Changes: - Rename packages/agentmemory-mcp → packages/mcp - Package name: agentmemory-mcp → @agentmemory/mcp (0.8.4 → 0.8.6) - Keep bin name `agentmemory-mcp` so `npm i -g @agentmemory/mcp` still installs a binary at `agentmemory-mcp` for muscle memory - Log prefix [agentmemory-mcp] → [@agentmemory/mcp] in standalone.ts and in-memory-kv.ts - README / integrations/openclaw / integrations/hermes / src/cli.ts all point at `npx -y @agentmemory/mcp` - .github/workflows/publish.yml working-directory and npm view queries target packages/mcp and @agentmemory/mcp - Shim dependency on @agentmemory/agentmemory bumped to ~0.8.6 - Main package 0.8.5 → 0.8.6 across the 8 version files - CHANGELOG [0.8.6] entry documenting the scope move |
||
|
Rohit Ghumare
|
8a36fe7867 |
fix: retention scoring (#119) + npx agentmemory-mcp 404 (#120), release 0.8.3 (#123)
* fix: retention scoring (#119) + npx agentmemory-mcp 404 (#120), release 0.8.3 Issue #119 — retention score ignored agent-side reads `mem::retention-score` previously hardcoded `accessCount=0` and `accessTimestamps=[]` for episodic memories and used only a single-sample `lastAccessedAt` for semantic memories, so the time-frequency decay formula was a dead path. All read endpoints now record access events to a new `mem:access` KV namespace via a keyed-mutex'd access tracker: - mem::search, mem::smart-search (compact + expand), mem::context, mem::timeline, mem::file-context, mem::get-related, mem::working-context - retention.ts pre-fetches the full access log in one kv.list call, normalizes every row defensively, and builds an O(1) lookup Map - recordAccessBatch uses Promise.allSettled so a slow keyed-lock on one id does not block the rest of the batch - Bounded ring buffer of the last 20 access timestamps per memory - Backwards-compat fallback: pre-0.8.3 semantic memories with only the legacy sem.lastAccessedAt still score correctly - Corrupt lastAccessedAt values are NaN-safe via Date.parse + isFinite - reinforcementBoost is reported as the raw formula output, not the clamped residual Memory deletion sites (retention-evict, evict, auto-forget, governance-delete, governance-bulk, forget, import replace) now call deleteAccessLog to prevent mem:access from accumulating zombie entries. mem::export / mem::import and mem::snapshot-create / mem::snapshot-restore round-trip the new namespace so backup/restore cycles no longer zero out reinforcement signals. Issue #120 — npx agentmemory-mcp returned npm registry 404 The README instructed users to run `npx agentmemory-mcp`, but `agentmemory-mcp` only existed as a `bin` entry inside `@agentmemory/agentmemory`, not a real registry package. Two-part fix: - New sibling package `packages/agentmemory-mcp/` — a thin shim that depends on `@agentmemory/agentmemory` (~0.8.3, tilde to block 0.9.x supply-chain drift) and forwards to dist/standalone.mjs via the new `exports` field on the main package - Canonical `npx @agentmemory/agentmemory mcp` subcommand on the CLI for users who already have the main package installed - Removed the dead `agentmemory-mcp` bin from the main package so the shim owns the name unambiguously - publish.yml publishes both packages in order with idempotent guards and npm-view registry polling (no more fixed sleep) - All MCP install snippets in README + integrations/openclaw + hermes + shim README use `npx -y agentmemory-mcp` to skip install prompts Release 0.8.3 - 670 tests passing (665 + 11 new: access tracker, retention, smart-search integration, corrupt-input, kv.list failure path, Promise.allSettled resilience) - Version bumped across package.json, src/version.ts, types.ts, export-import supportedVersions, plugin.json - package-lock.json regenerated * fix: address CodeRabbit review feedback on #123 Real issues caught and fixed: - access-tracker: deleteAccessLog now takes the same mem:access:<id> keyed mutex used by recordAccess, eliminating the race where a concurrent delete could drop an in-flight RMW update and leave a stale access log for an evicted memory - access-tracker: normalizeAccessLog now coerces count to a non-negative integer, drops non-finite recent[] entries, truncates recent[] to the last 20 on read (enforcing the ring-buffer invariant), and guarantees count >= recent.length so a malformed row can't produce NaN downstream. count is NOT capped at 20 — it is the lifetime access counter, while recent[] is the 20-entry window - export-import: import path now rejects accessLogs arrays above MAX_ACCESS_LOGS (50_000), normalizes each entry via normalizeAccessLog, and drops entries whose memoryId is not in the imported memories set, so a crafted export can't blow up memory or resurrect zombie access rows for memories that don't exist - publish.yml: added a post-publish npm view polling loop for agentmemory-mcp mirroring the one that already guards the main package, so the workflow only succeeds when `npx agentmemory-mcp` is actually visible on the registry - CHANGELOG.md: added the missing [0.8.3] reference-style link target at the bottom to match the [0.8.2]/[0.8.1]/[0.8.0] pattern - README.md: standalone MCP inline examples now use `npx -y` to match the MCP config snippets and skip the install confirmation prompt Tests: 680/680 (+10 new — deleteAccessLog behavior, normalizeAccessLog invariants, malformed mem:access row handling in retention scoring). Findings deliberately not applied: - auto-forget.ts / remember.ts / evict.ts recordAudit calls: existing pattern in the codebase only audits governance deletes (user-initiated admin actions), not automatic eviction. Adding audit everywhere is a policy change, out of scope for this PR - evict.ts gating deleteAccessLog on memory delete success: current order is defensible, deleteAccessLog is already best-effort with its own try/catch, and calling it after a failed memory delete is harmless - snapshot.ts fail-fast on kv.list failure: inconsistent with the existing .catch(() => []) pattern used for observations in the same function - retention.ts semantic evict only deletes KV.memories rows: real bug but pre-existing on main (RetentionScore has no source/type field). Tracked separately — out of scope for this PR - bin.mjs fallback command: already present in the existing catch handler - Promise.all parallelization of delete+deleteAccessLog: micro optimization not worth the readability cost |
||
|
Rohit Ghumare
|
79a7a8ec04 |
feat: real agent logos + paste-this-prompt blocks for integrations (#114)
* feat: flashy README with real agent logos + paste-this-prompt blocks for integrations ## Main README — real logos in Supported Agents grid Replaced plain text cells with real brand logos for all 16 supported agents: - simple-icons CDN for: Claude Code (Anthropic), Cursor, Gemini CLI (Google Gemini), Codex CLI (OpenAI), Windsurf, Claude Desktop, Claude SDK - GitHub org avatars for: OpenClaw, OpenCode (opencode-ai), Cline, Hermes (NousResearch), Goose (block), Kilo Code (kilo-org), Aider (Aider-AI), Roo Code (RooCodeInc) - Shield badge for the generic "Any agent" cell Each logo is clickable and links to the upstream project. The OpenClaw and Hermes cells now link directly to integrations/openclaw and integrations/hermes so users can find the deeper plugin integration. Added tagline footer below the grid reinforcing the cross-agent story. ## Integration READMEs — paste-this-prompt blocks Following the gstack pattern, both integration READMEs now open with a visual hero (upstream logo + agentmemory logo) and a copy-pasteable text block the user can drop into their agent. The agent handles the entire setup — start server, update MCP config, verify health, open viewer. This matches the "paste this into Claude Code" block we already have in the main README for Claude Code users. ### openclaw/README.md - Centered hero: OpenClaw org avatar + agentmemory icon - Shield badges: 43 MCP tools, 4 lifecycle hooks, 95.2% R@5, self-hosted - "Install it in 30 seconds" section with the paste-this prompt ### hermes/README.md - Centered hero: NousResearch avatar + agentmemory icon - Shield badges: 43 MCP tools, 6 lifecycle hooks, 95.2% R@5, self-hosted - "Install it in 30 seconds" section with the paste-this prompt All 654 tests still passing. * fix: reorder agents, replace broken logos, add OpenClaw/Hermes paste blocks, cleaner hero ## Main README ### Supported Agents grid — 3 fixes 1. **Reorder**: OpenClaw and Hermes now in positions 2 and 3 (right after Claude Code), since they have first-class gateway plugins in integrations/. Users shouldn't have to scroll to find them. 2. **Fix broken Codex logo**: simple-icons CDN returned 404 for the OpenAI slug with black color. Switched ALL logos to GitHub org avatars (github.com/<org>.png?size=120) which are bulletproof and always return real images. Verified 7/7 resolve to actual PNGs. 3. **Bigger logos**: bumped from 40px to 48px for more visual weight. ### Paste-this-prompt toggles Added two collapsible <details> blocks after the Claude Code paste prompt: one for OpenClaw, one for Hermes. Each contains a complete copy-pasteable setup prompt that the agent can execute, plus a link to the full integration guide. ## Integration README heroes — redesigned The old hero had two logos separated by an ugly gray "+" shield badge that looked cheap. Replaced with: - agentmemory banner.png as the centered hero image - H1 title with a small inline upstream logo (28px) next to the title - Bolded tagline + subtitle with upstream link - Shield badge row (MCP tools, hooks, R@5, self-hosted, license) Much cleaner and follows the main README's visual pattern. Verified: 654/654 tests passing. * Update README.md * feat: custom SVG tags for section headers (no emojis) Replaces emoji section headers with custom SVG badges matching the agentmemory brand style (orange #FF6B35 accent on dark #1A1A1A). Inspired by shanraisshan/claude-code-best-practice's custom tag approach in its !/ directory. ## Custom SVG tags created (30 total in assets/tags/) ### 14 section headers (section-*.svg) Each is a 44px-tall dark rounded badge with: - Orange gradient accent strip on the left (brand color #FF6B35 → #FF8F5E) - Uppercase title in white, 800 weight, 2.2 letter-spacing - Light gray subtitle (#9CA3AF) with section context - Subtle #2A2A2A border on dark #1A1A1A → #0F0F0F gradient Sections: works-with-every-agent, benchmarks, vs-competitors, quick-start, why, how-it-works, search, mcp-server, real-time-viewer, configuration, api, architecture, development, license. ### 6 hero stat blocks (stat-*.svg) Big numbers with small uppercase labels, replacing the shield.io badge row in two places (hero + benchmarks section): - stat-recall: 95.2% R@5 (green) - stat-tokens: 92% fewer tokens (green) - stat-tools: 43 MCP tools (orange) - stat-hooks: 12 auto hooks (orange) - stat-deps: 0 external DBs (purple) - stat-tests: 654 tests passing (green) ### 8 pill tags (pill-*.svg) Rounded pills with colored dot indicator for inline status tags: MCP, AUTO HOOK, SKILL, NEW, BETA, STABLE, PLUGIN, SECURE. ### 1 "New in v0.8.2" version tag Dark pill with orange v0.8.2 version marker. ### 1 section divider Horizontal line with orange diamond in the middle (unused for now, available for future sections). ## README changes - All <h2> section headers now use <img> tags pointing to the SVG - Hero stats row replaced with stat-*.svg row (same visual position) - Benchmarks stats row replaced with the same stat-*.svg row - Nav links updated to match the new h2 anchor IDs - "New in v0.8.2" callout uses new-v082.svg tag + note - Cursor grid cell fixed (was missing <strong>Cursor</strong> label) - Zero emojis in the entire README All 30 SVGs validated with xmllint, 654/654 tests passing. * Remove version 0.8.2 image from README Removed image tag for version 0.8.2 from README. |
||
|
Rohit Ghumare
|
ae8f061cd6 |
feat: demo command, benchmark comparison, OpenClaw integration (#113)
* feat: add demo command, benchmark comparison, OpenClaw integration, token cost in viewer
Product & ecosystem improvements surfaced from the last30days research
and competitive analysis of the AI agent memory space.
## New
### agentmemory demo command
Seeds 3 realistic sessions (JWT auth, N+1 query fix, rate limiting)
and runs smart-search queries against them. Shows token-aware semantic
search finding "N+1 query fix" when you search "database performance
optimization" — proof that keyword matching can't do that.
npx @agentmemory/agentmemory demo
Surfaces the "show don't tell" moment in 30 seconds without requiring
the user to integrate anything.
### benchmark/COMPARISON.md
Head-to-head comparison vs mem0 (53K stars, 68.5% LoCoMo),
Letta/MemGPT (22K stars, 83.2% LoCoMo), Khoj (34K stars),
claude-mem (46K stars), and Hippo. Feature matrix across 18
dimensions. Token efficiency table. Honest caveats about LongMemEval
vs LoCoMo apples-vs-oranges. Lets users compare without trusting our
README.
### integrations/openclaw/
OpenClaw gateway plugin following the same pattern as the Hermes
integration. README, plugin.yaml with hooks config, and plugin.mjs
implementing the 4 lifecycle hooks (on_session_start, on_pre_llm_call,
on_post_tool_use, on_session_end). Gets agentmemory into the OpenClaw
ecosystem for distribution.
## Improved
### Viewer token savings card
Now shows tokens saved AND dollar cost saved (using $0.30/1K as a
reasonable mid-tier model rate) instead of just raw numbers. Makes
the ROI immediately tangible.
### README additions
- "Try it in 30 seconds" section featuring the new demo command
- Competitor comparison link in benchmarks section
- OpenClaw integration link in supported agents table
* refactor: simplify demo command and OpenClaw plugin
- Extract postJson helper in cli.ts runDemo (4x repeated fetch boilerplate → single call site)
- Break runDemo into buildDemoSessions, seedDemoSession, runDemoSearch for single-responsibility
- Replace three-branch if/else command dispatch with a commands map (single error handler)
- Extract typed DemoSession/DemoObservation/SearchResult interfaces
- Simplify OpenClaw plugin.mjs: collapse headers() + fetchJson() into a single postJson method
Each hook is now ~5 lines instead of ~10
No behavior change. 654/654 tests passing, CLI help and error paths verified.
* fix: address CodeRabbit review on growth changes
## plugin.mjs
- Honor the enabled config flag: constructor now sets this.enabled and
all four hooks (onSessionStart, onPreLlmCall, onPostToolUse,
onSessionEnd) return early when disabled
- Fail-fast on non-OK HTTP: previously !res.ok returned null regardless
of fallbackOnError. Now throws with status/statusText/body when
fallbackOnError is false
- Update header JSDoc to use the real hook names instead of the
fictional prefetch/capture/consolidate
## openclaw README.md
- Replace stale hook names (prefetch/capture/consolidate) with the
actual onSessionStart/onPreLlmCall/onPostToolUse/onSessionEnd names
matching plugin.mjs
- Add 'text' language identifier to the Project profile code fence to
satisfy markdownlint MD040
## cli.ts
- Replace ad-hoc Date.now()-based session IDs with generateId("demo")
from src/state/schema.ts, matching the rest of the codebase
(snapshot.ts, migrate.ts, consolidation-pipeline.ts)
- Add postJsonStrict helper that throws on non-OK with status + body
- seedDemoSession now uses postJsonStrict for session/start and
session/end (critical lifecycle calls that should fail fast)
- The observation POST in the loop now inlines the fetch to surface
HTTP errors via p.log.warn with status/body, still only incrementing
the stored counter on success
## viewer/index.html
- Fix token-to-dollar conversion that was 100x underreporting:
tokensSaved / 1000 * 0.3 returns DOLLARS, not cents. Now computes
dollars first, then cents = Math.round(dollars * 100)
- 100K tokens saved now correctly displays $30.00, not 30ct
All 654 tests still passing.
* fix: address 2 more CodeRabbit findings on plugin.mjs
- Use nullish coalescing (??) for config defaults so valid falsy
values like min_confidence: 0 or timeout_ms: 0 aren't overwritten
by defaults. || would clobber them.
- Fix /agentmemory/context payload to match the server contract at
src/triggers/api.ts:115. The handler expects { sessionId, project,
budget? } but the plugin was sending { sessionId, query, tokenBudget,
minConfidence }. Three issues:
1. Missing required 'project' field
2. Wrong field name: 'tokenBudget' should be 'budget'
3. 'query' and 'minConfidence' are not part of this endpoint's
contract (probably belong on /smart-search instead)
|
||
|
Rohit Ghumare
|
9173b090f4 |
fix: address review findings on Hermes plugin
- SSRF prevention: validate URL scheme (http/https only) before urlopen - on_pre_compress: inject fetched context into messages list (was no-op) - Remove unused self._secret; _api reads from env directly |
||
|
Rohit Ghumare
|
112e6f4bc0 |
feat: add Hermes Agent memory provider plugin
Two integration paths: 1. MCP server (zero code) - add to ~/.hermes/config.yaml 2. Memory provider plugin (deeper) - hooks into Hermes agent loop Plugin implements the full MemoryProvider ABC: - prefetch() injects relevant memories before each LLM call - sync_turn() captures conversation turns in background (non-blocking) - on_session_end() marks sessions for summarization - on_pre_compress() re-injects context before compaction - on_memory_write() mirrors MEMORY.md writes - system_prompt_block() injects project profile - 3 tools: memory_recall, memory_save, memory_search Uses only stdlib (urllib, json, threading). No new dependencies. |