English · 中文
1. Install
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
Other MCP clients: { "mcpServers": { "agent-recall": { "command": "npx", "args": ["-y", "agent-recall-mcp"] } } }
에이전트 강화
게시자의 자체 명령입니다. PlugMCP 엔드포인트가 아닙니다.
Host a copy with our keys and logs.
npx -y [email protected]Claude Code에는 로컬 명령용 설치 링크가 없습니다. 아래 명령을 복사해 터미널에서 실행합니다.
claude mcp add goldentrii-agentrecall-x -- npx -y agent-recall-mcp@3.5.2터미널에서 실행합니다.
{ "mcpServers": { "goldentrii-agentrecall-x": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
원격 URL인가요, 내 컴퓨터에서 실행하는 명령인가요? 두 설치 방식의 차이
PlugMCP에서 실행
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
실행게시자 제공
English · 中文
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
Other MCP clients: { "mcpServers": { "agent-recall": { "command": "npx", "args": ["-y", "agent-recall-mcp"] } } }
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
"I installed AgentRecall. From now on, when you correct me, I save it as a rule on your disk — plain markdown in
~/.agent-recall/, nothing leaves the machine. Next session I load those rules before I start, so you shouldn't have to say the same thing twice. Say 'save' anytime and I'll checkpoint."
On session start → call session_start (before you act)
When the human corrects you → call remember with type "correction" — saying "noted" is not saving
Before publish/push/deploy/delete → call check with action_description; obey verdict "blocked"
When past context would help → call recall
On "save" / "remember" / exit → call session_end
You tell your agent "don't bump the version without asking." It apologizes, fixes it, and the session ends. Next week a fresh session does it again — the correction lived in a chat log nobody reads.
AgentRecall turns that sentence into a structured, persistent rule, puts it in front of the next agent before it acts, and records whether the mistake came back.
── session 3 ─────────────────────────────────────────────
you › no — never bump the version without asking me first
agent › remember(type: "correction")
✓ saved · severity p0 · applies_when: [release, npm]
── session 9 · new agent, no chat history ───────────────
session_start › project "my-app" · 1 critical correction
watch_for: version bump → ask the owner first
you › ship the fix
agent › Fix is merged. Want me to bump to 1.4.1, or leave the version?
outcome recorded: heeded
Illustrative transcript.
AgentRecall is two things:
applies_when, retraction, outcome — that persists across sessions, projects and agent restarts. Export format: corrections-export/v1, scrubbed on egress.retrieved_count, and every time the agent meets the same situation the outcome is logged as heeded or recurred. No public benchmark measures that step; we built the harness first and publish what it finds, including the unflattering numbers.flowchart LR
A([session start]) --> B["/arstart · session_start<br/>load rules + context"]
B --> C{work}
C -->|need past knowledge| D["/arrecall · recall"]
D --> C
C -->|corrected| R["remember<br/>type: correction"]
R --> L[(corrections<br/>ledger)]
C -->|risky action| K["check"]
L -.-> K
C --> E["/arsave · session_end<br/>journal + compound"]
E --> F([session end])
L -. watch_for .-> B
F -. every K sessions .-> G["/arreflect<br/>consolidate"]
G -.-> A
Without
/arstart, a fresh agent has zero orientation. Without/arsave, nothing compounds.
Five tools ship by default. Each description is written for the agent and says when to call it.
List what your install exposes: npx -y agent-recall-mcp --list-tools.
[!IMPORTANT] The Automaticity Law — why only 5. Memory only compounds if it fires without being asked. Across 44 projects and weeks of real use, the pull tools (
recall,memory_query) saw zero organic calls — including from the agent that built them. Push channels (session_start,session_end, correction hooks) are what change behavior. Every extra default tool costs definition tokens every session for no return. (Self-measured on the owner's store, 2026-06-12.)So on Claude Code, wire the hooks — the loop then runs without agent discipline:
ar hook-start SessionStart load context, show watch_for warnings ar hook-correction UserPromptSubmit capture corrections silently ar hook-ambient UserPromptSubmit inject relevant memories (≥2-word overlap floor) ar hook-save UserPromptSubmit "save"/"retain" → prompt session_end ar hook-pretool PreToolUse warn on npm publish, git push, rm -rf, deploy, DROP TABLE ar hook-end SessionEnd auto-save journal if not saved today ar health — recent hook failures (fail-loud)
The cognitive-psychology taxonomy, mapped to plain files. Each layer forgets at a different speed, because human memory does.
~/.agent-recall/
├── projects/<slug>/
│ ├── journal/ episodic — one entry per session
│ ├── corrections/ behavioral rules + outcome ledger
│ └── palace/
│ ├── rooms/ semantic
│ ├── skills/ procedural
│ ├── pipeline/ narrative
│ ├── identity.md
│ └── awareness cross-project insights
├── dreams/ nightly consolidation reports
├── dashboard.html human-readable
└── dashboard.json agent-readable snapshot
All layers share one naming grammar, so an agent can compose a retrieval path from intent. Older files keep working through a legacy_path view — no migration.
flowchart LR
C["correction<br/>(remember / hook)"] --> L[(ledger)]
L --> S["session_start<br/>ranked by severity,<br/>proof, recency"]
S --> O{"same situation<br/>again?"}
O -->|heeded| P["proof_count +1<br/>stability × 1.3"]
O -->|recurred| X["phantom<br/>→ /arreflect<br/>rewrites the rule"]
P --> A["≥ 3 confirmations<br/>→ awareness<br/>(cross-project)"]
X --> L
A correction gets stronger each time it is confirmed, weaker when it is marked unhelpful, and graduates to every project once it has been confirmed on three distinct (day, project) occasions. A rule that was saved but whose mistake came back is a phantom — the write cost was paid and behavior never changed — and gets re-written, not just re-saved.
Most of the field ships "AI memory" as a black box. Every mechanism in AgentRecall is a formula you can read, with its constants in the source and an honest label:
Palace, journal, insight and corrections each rank their own candidates; the lists are merged by rank, never by raw score, because the raw scores live on incomparable scales (Cormack, Clarke & Büttcher 2009 — the same $k$ Elasticsearch ships):
\mathrm{RRF}(d) \;=\; \sum_{\ell \,\in\, \text{lists}} \frac{w_\ell}{k + \mathrm{rank}_\ell(d)}, \qquad k = 60,\;\; w_\ell = 1
The optional semantic leg is just one more list with $w = 1.0$ — a weight measured, not chosen: 1.1 and 1.3 flooded the top-5.
[!NOTE] The math found a bug. Adjacent RRF ranks differ by only $
\frac{1/(60+r)}{1/(61+r)} \approx 1.6\%$, so any post-fusion multiplier above ≈1.02 vaults an off-topic item over every on-topic one. The old ×3 / ×2 / ×1.3 "recent-item boost" did exactly that — top-5 filled with the last 72 h of diary lines. Removing it: 55.0% → 75.0% top-5 hit-rate on the golden set (twin-clone control, 2026-09-12).
R(t) = e^{-t/S}, \qquad S_{\text{journal}} = 2,\;\; S_{\text{knowledge}} = 180,\;\; S_{\text{palace}} = 9999 \text{ days}
A two-component (stability, retrievability) simplification of FSRS-6 / SuperMemo — no difficulty term, because we never run review sessions:
R = e^{-\Delta t / S}, \qquad S_0 = 7\text{ d}, \qquad \underbrace{S' = 1.3\,S}_{\text{confirmed}}, \qquad \underbrace{S' = \max(1,\; 0.5\,S)}_{\text{marked wrong}}
Buckets: $R \ge 0.85$ hot · $\ge 0.6$ warm · $\ge 0.3$ cool · else archive candidate — surfaced on a dashboard, never auto-deleted.
\text{salience} = 0.30\,\text{recency} + 0.25\,\text{access} + 0.20\,\text{connections} + 0.15\,\text{urgency} + 0.10\,\text{importance}
with $\text{recency} = \max(0.05,\; \rho_c^{\,\text{days}})$, where the decay rate depends on category: goal $\rho = 0.99$ · architecture $0.98$ · decision / lesson $0.97$ · observation $0.95$ · blocker $0.90$. Self-reported importance is deliberately the weakest term — people mis-estimate it; what you actually use is the stronger signal.
Every recall result can be rated useful / not useful. The item's score is multiplied by twice its Laplace-smoothed posterior mean (neutral = ×1.0; the only post-fusion score change on default paths):
\mathbb{E}[\theta] = \frac{\text{pos}+1}{\text{pos}+\text{neg}+2}, \qquad \text{multiplier} = 2\,\mathbb{E}[\theta] \in (0, 2)
AGENT_RECALL_ACTIVATION=1)Memories cited together become linked. The associative term of ACT-R's declarative-memory equation (Anderson & Lebiere):
A_i = B_i + \sum_j W_j\, S_{ji}, \qquad S_{ji} = w_{ji}\, e^{-\Delta d / 30}, \qquad W_j = \tfrac{1}{|\text{context}|}
Re-rank: $\text{score}' = \text{score}\cdot\bigl(1 + 0.2\,\tfrac{x}{x+1}\bigr)$ — the $\tfrac{x}{x+1}$ squash keeps two incompatible scales from being summed, and is an exact no-op when there is no evidence.
\cos(A,B) = \frac{|A \cap B|}{\sqrt{|A|\,|B|}}, \qquad \text{sim} = \max\bigl(\cos_{\text{concepts}},\; \cos_{\text{char-trigrams}}\bigr) \ge 0.20
Over stems + 13 hand-curated synonym groups ("publish / ship / release" collapse to one concept). It is fuzzy-lexical, not meaning. The 0.20 threshold is tuned by leave-one-out (predict-loo) as the highest-recall point that still holds 0% false positives.
Nightly consolidation used to gate on $\tfrac{\text{obs}}{7}\times\text{recency} \ge 0.8$. At 2 AM the freshest journal is yesterday, so recency $\le 0.85$ and "3 observations in 7 days" scored $\tfrac{3}{7}\times 0.85 = 0.36$ — silently discarded for 22 nights, while uptime monitoring stayed green. The replacement separates admission from promotion:
\text{promote} \iff \#\{(\text{day},\,\text{project}) \text{ confirmations}\} \ge 3
and every night now writes a yield record, so a zero-output night is classified (empty-corpus · filtered · already-known · errored) instead of looking healthy.
\text{heed} = \frac{\text{heeded}}{\text{heeded} + \text{recurred}}, \qquad
\text{CI}_{95} = \frac{\hat p + \frac{z^2}{2n} \;\pm\; z\sqrt{\frac{\hat p(1-\hat p)}{n} + \frac{z^2}{4n^2}}}{1+\frac{z^2}{n}}, \quad z = 1.96
Small $n$ gets an honest, wide interval instead of a confident point. Events are tiered by evidence (heeded_verified · heeded_checkaction · heeded_default · recurred_verified · recurred_selfreport), and every KPI surface shows both tiers as a range — absence of evidence is not credited as "heeded."
\text{conf} = \frac{\text{score}}{0.12}\;(\text{local RRF}) \;\;\big|\;\; \frac{\text{score}}{0.049}\;(\text{Supabase RRF}) \;\;\big|\;\; \cos\;(\text{vectors}) \;\;\longrightarrow\;\; \text{high} \ge .66,\; \text{med} \ge .40,\; \text{low} \ge .20
Ramsauer et al. 2020, implemented with a numerically stable softmax, $\beta = 8$:
\xi^{\text{new}} = X^{\top}\operatorname{softmax}(\beta X \xi), \qquad E = -\tfrac{1}{\beta}\log\sum_i e^{\beta\langle x_i,\xi\rangle} + \tfrac12\lVert\xi\rVert^2
Not on the default path: the co-citation graph is sparse by construction, and Hopfield's exponential-capacity argument assumes a dense regime — it would mostly attend to non-edges. The linear ACT-R sum is the right primitive for a sparse graph.
Today, accumulated corrections are clustering + decay + set-cosine: a tally, not a posterior. Calling that "intent reconstruction" would overstate it. The model that would earn the phrase treats each correction as a noisy sample of a latent preference $\theta$, with $x_i = \theta + \varepsilon_i,\; \varepsilon_i \sim \mathcal N(0, \sigma^2 I)$ and prior $\theta \sim \mathcal N(\mu_0, \tau^2 I)$:
\operatorname{Var}[\theta \mid x_{1..N}] = \Bigl(\frac{1}{\tau^2} + \frac{N}{\sigma^2}\Bigr)^{-1} = O\!\left(\frac{\sigma^2}{N}\right),
\qquad \mathrm{SNR}_N = \frac{\lVert \mu_N \rVert^2}{\operatorname{tr}\operatorname{Var}[\theta \mid x_{1..N}]}
Falsifiable claim: $\mathrm{SNR}_N$ rises monotonically for a consistent correction stream and stalls when corrections conflict. Want to build it? This is the most important open problem in the repo.
Full derivations, inputs, and every constant's provenance: packages/core/src/MATH.md.
Agent-memory benchmarks test retrieval. None tests whether a correction changes what a fresh agent does. Here is what our own instrument says — including the parts that make us look bad.
🔁 regenerates from this repo · 🔒 self-measured on the owner's private store, not reproducible here. Brackets are 95% intervals. The 80.8% embeddings leg is measured locally with the opt-in model (CI never downloads it, so no artifact is committed). Timings are machine-dependent; CI gates schema and determinism, never timing values.
We captured about a third of real corrections in our own use. The heed instrument used to default to "heeded" without evidence — it was reset to "unknown," so 0/3 is the honest starting point, not a regression (the pre-reset 92.5% is an instrument-biased upper bound; do not cite it). Offline transfer scores 0 on our corpus because 32 active corrections across 19 projects is too sparse to front-run mistakes — a density problem, not a retrieval one (confirmed 5× internally). Transfer recall cannot support a point estimate below 39 classes (claim-gate ledger, benchmark spec §2.6).
The fixture numbers are smaller than the lived-in ones because golden-v1 is synthetic and thin (3 projects). Every remaining fixture miss is a committed structural trap: pipeline dir, loose rooms file, cross-project silo.
Reproduce everything: docs/eval/REPRODUCE.md.
Competitor figures are their own published numbers, not measured side by side. Landscape: docs/research/agent-memory-landscape-2026-07.md.
# Claude Code
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
# Codex
codex mcp add agent-recall -- npx -y agent-recall-mcp
// Cursor — .cursor/mcp.json · Windsurf — ~/.codeium/windsurf/mcp_config.json
{ "mcpServers": { "agent-recall": { "command": "npx", "args": ["-y", "agent-recall-mcp"] } } }
// VS Code — .vscode/mcp.json
{ "servers": { "agent-recall": { "command": "npx", "args": ["-y", "agent-recall-mcp"] } } }
mkdir -p ~/.claude/skills/agent-recall
curl -o ~/.claude/skills/agent-recall/SKILL.md \
https://raw.githubusercontent.com/Goldentrii/AgentRecall-X/main/SKILL.md
import { AgentRecall } from "agent-recall-sdk";
const memory = new AgentRecall({ project: "my-app" });
await memory.capture("What stack?", "Next.js + Postgres");
const ctx = await memory.recall("rate limiting");
Each instance gets its own isolated root (AsyncLocalStorage), so concurrent instances never share state.
npx agent-recall-cli recall "rate limiting"
ar bootstrap # scan git repos, Claude AutoMemory, CLAUDE.md files (read-only, secrets untouched)
ar bootstrap --import # import what it found
Keyword recall can't reach a memory phrased differently ("semver increment" vs "one version bump per release"). The opt-in semantic leg uses a local ONNX model and joins the same RRF fusion as one more list.
ar embeddings setup # one-time: local runtime (~380 MB) + model (~145 MB), cached
ar embeddings rebuild # incremental — only new/changed content embeds
export AGENT_RECALL_EMBEDDINGS=1
ar embeddings status
Needs a live Claude Code login (claude login if it stops).
experimental/harness-kit/ — Claude Code hooks that answer "did the correction change behavior?": a SessionStart scoreboard, an error-class taxonomy with mechanical phantom detection (violation dated after its rule), an overdue-reflection nudge, and an optional model-dispatch guard. North-star: post-re-abstraction phantom rate → 0. First run: 8 error classes and 18 phantoms in 109 corrections; 6 rules re-abstracted the same day. Python 3 stdlib only.
packages/
├── core/ storage, retrieval, math, tool logic agent-recall-core
├── mcp-server/ thin MCP wrappers agent-recall-mcp
├── sdk/ programmatic API agent-recall-sdk
└── cli/ the `ar` command + hooks agent-recall-cli
flowchart LR
Q[query] --> T[tokenize · stem<br/>synonyms · IDF]
T --> P[palace<br/>0.9 key + 0.1 salience]
T --> J[journal<br/>0.5 recency + 0.5 exact]
T --> I[insights<br/>relevance · exact · confirm]
T --> K[corrections<br/>exact · severity · proof]
Q -. opt-in .-> V[local embeddings<br/>cosine top-8]
P & J & I & K & V --> F["RRF Σ w/(60+rank)"]
F --> B["× Beta feedback"]
B --> C[calibrated confidence]
C --> R[results + alsoLinked]
All memory is local markdown. An optional Supabase mirror adds pgvector recall with the same RRF fusion; all-local stays the default. Writes go through a progress-aware file lock with NTFS-safe release; alignment and feedback logs are append-only NDJSON.
CI runs build + regression + tests on ubuntu-latest and windows-latest.
[!TIP] The 15-minute contribution that matters most. The field has vendor-selected positives and no external baselines for behavior change. Use AgentRecall for a week, then:
git clone https://github.com/Goldentrii/AgentRecall-X.git && cd AgentRecall-X npm ci && npm run bench # reads your local ~/.agent-recall corpusPost the result in Discussions → Benchmark Numbers — a low score is a valid result. More in CONTRIBUTORS-WANTED.md.
Thanks to @buer5, @lonelyhty and 雷昊 for the Windows portability work and fixes that shipped in 3.5.x.
PRs welcome. Open an issue first for anything substantive — the design is opinionated and grounded in published research, and we want changes grounded the same way: a formula, a label, and a measurement.
MIT — see LICENSE.
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
{ "mcpServers": { "goldentrii-agentrecall-x": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}도구
아직 도구 목록이 없습니다. 원격 서버는 첫 상태 확인 후에 도구 목록이 생깁니다.
FAQ
이 페이지에서 Cursor, Claude Desktop, Claude Code 또는 VS Code용 stdio 설정을 복사합니다. PlugMCP 프록시가 아니라 게시자의 설치 방식을 사용합니다.
이 레코드에는 필수 환경 변수가 등록되어 있지 않습니다.
AgentRecall X은(는) stdio를 통해 로컬에서 실행됩니다.
마지막 확인: 2026-11-17. Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.