recallnest
AliceLJY/recallnest
One memory, three terminals. Shared memory layer for Claude Code, Codex, and Gemini CLI — hybrid retrieval (vector + BM25 + KG), session continuity, 41 MCP tools. Local-first, LanceDB-backed.
Instalação
npx convez-ai AliceLJY/recallnest1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
README
A tradução para o português deste README ainda está na fila.
RecallNest
Shared Memory Layer for Claude Code, Codex, and Gemini CLI
One memory. Three terminals. Context that survives across windows.
A local-first memory system backed by LanceDB that turns scattered conversation history into reusable knowledge — shared across your coding agents, recalled automatically.
Why RecallNest?
Coding agents forget everything between windows. Your context — project configs, debugging decisions, entity mappings — is scattered across Claude Code, Codex, and Gemini CLI with no shared memory.
RecallNest solves this: a single LanceDB-backed memory layer that your coding agents read and write. Context stored in one window is auto-recalled in another. Sessions checkpoint on exit and resume on start. Memory decays, evolves, and self-organizes — not just raw log storage.
Quick Start
Option A: Claude Code Plugin (recommended)
/plugin marketplace add AliceLJY/recallnest
/plugin install recallnest@AliceLJY
RecallNest starts automatically with Claude Code. No manual MCP config needed.
Requires: Bun (recommended) or Node.js 18+. Dependencies install on first start.
Option B: npm install
npx recallnest --help # run directly
# or
npm install -g recallnest # install globally
recallnest doctor
Works with Node.js 18+ (via tsx) or Bun. No git clone needed.
Option C: Manual setup
git clone https://github.com/AliceLJY/recallnest.git
cd recallnest
bun install
cp config.json.example config.json
cp .env.example .env
# Edit .env → add your JINA_API_KEY
Start the server
bun run api
# → RecallNest API running at http://localhost:4318
Try it
# Store a memory
curl -X POST http://localhost:4318/v1/store \
-H "Content-Type: application/json" \
-d '{"text": "User prefers dark mode", "category": "preferences"}'
# Recall memories
curl -X POST http://localhost:4318/v1/recall \
-H "Content-Type: application/json" \
-d '{"query": "user preferences"}'
# Check stats
curl http://localhost:4318/v1/stats
Connect your terminals
bash integrations/claude-code/setup.sh
bash integrations/gemini-cli/setup.sh
bash integrations/codex/setup.sh
Each script installs MCP access and managed continuity rules, so resume_context fires automatically in fresh windows.
Index existing conversations
bun run src/cli.ts ingest --source all
bun run seed:continuity
bun run src/cli.ts doctor
Web UI
bun run src/ui-server.ts
# → http://localhost:4317
Core Capabilities
Access & Setup
| Capability | Description |
|---|---|
| CC Plugin | Install in Claude Code with one command — no manual config |
| Shared Index | One LanceDB store for Claude Code, Codex, and Gemini CLI |
| Dual Interface | MCP (stdio) for CLI tools + HTTP API for custom agents |
| One-Click Setup | Integration scripts install MCP access and continuity rules |
Recall & Continuity
| Capability | Description |
|---|---|
| Hybrid Retrieval | 6-channel: vector + BM25 + L0/L1/L2 multi-vector + KG graph (PPR) |
| 4 Retrieval Profiles | default, writing, debug, fact-check — tuned for different tasks |
| Session Continuity | checkpoint_session + resume_context (full/light/summary modes) with repo-state guard |
| Session Distiller | 3-layer conversation compression: microcompact → LLM summary → knowledge extraction |
| Conversation Import | Import from Claude Code, Claude.ai, ChatGPT, Slack, and plaintext |
| Topic Tags | Intra-scope topic partitioning — auto-detected, filterable in search |
Memory Lifecycle & Governance
| Capability | Description |
|---|---|
| Memory Evolution | Supersede chains, decay scoring, LLM importance, consolidation, archival |
| Smart Promotion | Evidence → durable memory with conflict guards, merge resolution, and audit trail |
| Privacy Tiers | 4-tier (ephemeral / private / durable / shared) with cascade forgetting |
| Admission Control | Write-time gating: noise filter, importance floor, dedup, rate limiting |
| Memory Lint | Contradiction, duplicate, stale, and orphan detection with health score |
| Offline Consolidation | dream command: clustering, merging, pruning of accumulated memories |
Reasoning & Structure
| Capability | Description |
|---|---|
| Knowledge Graph | Entity relation graph with PPR algorithm for multi-hop questions |
| Constructive Retrieval | Multi-source candidate expansion + grounded context reconstruction |
| Narrative Architecture | 3-layer autobiographical metadata (life-period → general-event → specific-event) |
| Skill Memory | Store, retrieve, and promote executable skills from recurring patterns |
| Predictive Reminders | Behavioral-signal prediction engine surfaces "you might need this" suggestions |
| 6 Categories | profile, preferences, entities, events, cases, patterns — with category-aware merge strategies |
Visibility & Operations
| Capability | Description |
|---|---|
| Dashboard | Web UI with stats, category distribution, growth trends, and health |
| Workflow Observation | Dedicated append-only workflow health records, outside regular memory |
| Structured Assets | Pins, briefs, and distilled summaries — not just raw logs |
| Data Checkup | Data quality health checks on the memory store (including source health) |
| Source Heartbeats | Automatic ingest health tracking per data source with staleness alerts |
| Export Graph | Export interactive HTML knowledge graph visualization |
| Batch Operations | Store up to 20 memories in a single call with dedup |
| Connector Framework | Standard connector-v1 format for external data sources with example adapters |
New in v2.1: Philosophy-Informed Memory
v2.0 built the operational memory platform; v2.1 added philosophy-informed memory behavior.
Five upgrades derived from 9 research dimensions in philosophy of memory, each mapped to concrete engineering:
-
Emotion-Aware Decay (Affective Memory Theory) — Memories with strong emotional content decay 20-30% slower. Keyword-based emotion detection computes
salience(mnemonic significance), which feeds into the Weibull half-life formula and a rebalanced 4-factor evolution score. Zero LLM cost. -
Memory Ethics Layer (Right to Be Forgotten / GDPR Art. 17) — Four privacy tiers (
ephemeral/private/durable/shared). Cascade forgetting engine that propagates deletion through KG triples, evolution chains, pin assets, and briefs. Full audit trail.forget_memoryMCP tool for agent-driven deletion. -
Autobiographical Narrative (Narrative Identity Theory / Conway's 3-layer model) — Memories are tagged with
lifePeriod → generalEvent → specificEventhierarchy, orthogonal to existing 6 categories. Retrieval pulls narrative siblings. Context rendering groups by life period. Rule-based tagger with EN+CN support. -
Constructive Retrieval (Simulation Theory / Michaelian) — Instead of returning raw stored text, RecallNest now reconstructs context from an expanded candidate set: KG neighbors + evolution chains + cluster members + narrative siblings. Source-map grounded coverage replaces lexical overlap. Contradictions are detected and flagged.
-
Predictive Prospective Memory (Mental Time Travel / Tulving) — Heuristic prediction engine that surfaces "you might need this" reminders from behavioral signals: stale checkpoint open loops, corrected workflow observations, high-frequency dormant memories, and uncovered query topics. Zero LLM cost. Auto-expire in 7 days if unaccepted.
New in v2.2: Retrieval Quality Hardening
v2.1 added philosophy-informed behavior; v2.2 closes the last three engine-layer gaps identified by a frontier research scan (ACC, PI-LLM, TSM).
-
Memory Confidence Meta-tags (ACC / Dual-Process UQ) — Each memory now carries structured
ConfidenceMetadata(score, reliability tier:direct/inferred/hearsay). Auto-assigned from source on write (manual= 0.9,agent= 0.7,conversation_import= 0.5). Retrieval scores are weighted by confidence.resume_contexttags low-confidence items with[低置信]. -
Interference Detection + Active Forgetting Gate (PI-LLM / SleepGate) — Semantic cluster detection identifies groups of near-duplicate memories competing for retrieval. Enhanced RIF keeps only top-K (default 3) per cluster; extras are demoted 50% instead of removed. Write-time pre-warning: when a scope accumulates ≥5 high-similarity active memories, the weakest is flagged
pending_review.data_checkupreports interference density. -
Temporal Validity Windows (TSM / TiMem / Zep) —
store_memoryacceptsvalidUntil(expiration) andeventTime(when the event actually happened).search_memorysupportsvalidAt(point-in-time query) andincludeExpired(demote 80% instead of hide). Auto-GC applies 2× decay acceleration to expired memories.
New in v2.3: Connector Ecosystem + Source Health
v2.2 hardened retrieval quality; v2.3 opens RecallNest to external data sources with a standard connector framework and operational health monitoring.
-
Connector-v1 Standard (GB-2) — A JSON format (
ConnectorOutputV1) that any external script can produce. Obsidian vaults, emails, RSS feeds, log files — normalize once, ingest through the full dedup/embed/extract pipeline. Seedocs/connector-spec.mdfor the specification andconnectors/examples/for adapter skeletons (email, logs, RSS). -
Obsidian Vault Ingestion (GB-1) — First-party Obsidian connector: scans
.mdfiles, extracts frontmatter + wikilinks, maps folder structure to tags. One command:lm ingest --obsidian /path/to/vault. -
Source Health Monitoring (GB-3) — Every connector ingest writes a heartbeat to
data/source-heartbeat.json.data_checkupflags stale sources (>7d warning, >30d error).doctor --cishows a per-source heartbeat summary with human-readable age.
Architecture
┌──────────────────────────────────────────────────────────┐
│ Client Layer │
├──────────┬──────────┬──────────┬──────────────────────────┤
│ Claude │ Gemini │ Codex │ Custom Agents / curl │
│ Code │ CLI │ │ │
└────┬─────┴────┬─────┴────┬─────┴──────┬──────────────────┘
│ │ │ │
└──── MCP (stdio) ───┘ HTTP API (port 4318)
│ │
▼ ▼
┌──────────────────────────────────────────────────────────┐
│ Integration Layer │
│ ┌─────────────────────┐ ┌────────────────────────────┐ │
│ │ MCP Server │ │ HTTP API Server │ │
│ │ 41 tools │ │ 21 endpoints │ │
│ └─────────┬───────────┘ └──────────┬─────────────────┘ │
└────────────┼─────────────────────────┼───────────────────┘
└──────────┬──────────────┘
▼
┌──────────────────────────────────────────────────────────┐
│ Core Engine │
│ │
│ ┌────────────┐ ┌────────────┐ ┌─────────────────────┐ │
│ │ Retriever │ │ Classifier │ │ Context Composer │ │
│ │ (vector + │ │ (6 cats) │ │ (resume_context) │ │
│ │ BM25 + RRF)│ │ │ │ │ │
│ └────────────┘ └────────────┘ └──────────────────────┘ │
│ ┌────────────┐ ┌────────────┐ ┌─────────────────────┐ │
│ │ Decay │ │ Conflict │ │ Capture Engine │ │
│ │ Engine │ │ Engine │ │ (evidence → durable) │ │
│ │ (Weibull) │ │ (audit + │ │ │ │
│ │ │ │ merge) │ │ │ │
│ └────────────┘ └────────────┘ └──────────────────────┘ │
└──────────────────────────┬───────────────────────────────┘
▼
┌──────────────────────────────────────────────────────────┐
│ Storage Layer │
│ ┌─────────────────────┐ ┌────────────────────────────┐ │
│ │ LanceDB │ │ Jina Embeddings v5 │ │
│ │ (vector + columnar) │ │ (1024-dim, task-aware) │ │
│ └─────────────────────┘ └────────────────────────────┘ │
└──────────────────────────────────────────────────────────┘
Internal Design
- L0 / L1 / L2 Dynamic Folding — every memory stores 3 granularity layers (one-liner / bullet summary / full content); retrieval dynamically selects which layer to return based on relevance score and token budget
- Weibull Decay + Emotion Modulation — memories decay along a parametric Weibull curve; importance scores modulate the half-life, and emotional salience extends it further (up to 30%)
- Vector Pre-filter + LLM Dedup — 90% of dedup decisions use cheap cosine similarity (>= 0.92); only borderline cases invoke LLM judgment, keeping costs low without sacrificing accuracy
- Category-Aware Merge Strategies —
profileandpreferencesuse merge-on-conflict (latest wins);eventsandcasesuse append-only (history preserved) - Display Score vs Elimination Score — dual-track retrieval: tier floor prevents core memories from ever dropping out, while decay boost lets fresh memories surface temporarily without permanently displacing stable ones
Full architecture deep-dive:
docs/architecture.md
Interfaces
RecallNest serves two interfaces:
- MCP — for Claude Code, Gemini CLI, and Codex (native tool access)
- HTTP API — for custom agents, SDK-based apps, and any HTTP client
Agent framework examples
Examples live in integrations/examples/:
| Framework | Example | Language |
|---|---|---|
| Claude Agent SDK | memory-agent.ts | TypeScript |
| OpenAI Agents SDK | memory-agent.py | Python |
| LangChain | memory-chain.py | Python |
| Tool | Description |
|---|---|
workflow_observe | Store an append-only workflow observation outside regular memory |
workflow_health | Inspect workflow observation health or show a degraded-workflow dashboard |
workflow_evidence | Build an evidence pack for a workflow primitive |
store_memory | Store a durable memory for future windows |
store_workflow_pattern | Store a reusable workflow as durable patterns memory |
store_case | Store a reusable problem-solution pair as durable cases memory |
promote_memory | Explicitly promote evidence into durable memory |
promote_scan | Scan recent evidence and auto-promote qualifying memories into durable storage |
list_conflicts | List or inspect promotion conflict candidates |
audit_conflicts | Summarize stale/escalated conflict priorities |
escalate_conflicts | Preview or apply conflict escalation metadata |
resolve_conflict | Resolve a stored conflict candidate (keep / accept / merge) |
checkpoint_session | Store the current active work state outside durable memory |
latest_checkpoint | Inspect the latest saved checkpoint by session or scope |
resume_context | Compose startup context for a fresh window |
search_memory | Proactive recall at task start |
explain_memory | Explain why memories matched |
distill_memory | Distill results into a compact briefing |
brief_memory | Create a structured brief and re-index it |
pin_memory | Promote a scoped memory into a pinned asset |
export_memory | Export a distilled memory briefing to disk |
list_pins | List pinned memories |
list_assets | List all structured assets |
list_dirty_briefs | Preview outdated brief assets created before the cleanup rules |
clean_dirty_briefs | Archive dirty brief assets and remove their indexed rows |
memory_stats | Show index statistics |
memory_drill_down | Inspect a specific memory entry with full metadata and provenance |
auto_capture | Heuristically extract and store memory signals from text (zero LLM calls) |
set_reminder | Set a prospective memory reminder to surface in a future session |
consolidate_memories | Cluster near-duplicate memories and merge them (dry-run by default) |
store_skill | Store an executable skill with trigger conditions and verification |
retrieve_skill | Retrieve matching executable skills by semantic similarity |
scan_skill_promotions | Scan cases/patterns for promotion candidates to skills |
list_tools | Discover available tools by tier (core/advanced/full) |
batch_store | Store up to 20 memories in a single call with dedup |
distill_session | Distill a conversation into structured knowledge via 3-layer pipeline |
import_conversations | Import conversations from Claude Code, ChatGPT, Slack, and more |
data_checkup | Run data quality health checks on the memory store |
dream | Run offline memory consolidation (clustering, merging, pruning) |
memory_lint | Run memory quality checks: contradictions, duplicates, stale entries, orphans |
forget_memory | Cascade-delete a memory with KG cleanup, pin archival, and audit trail |
export_graph | Export memories as an interactive HTML knowledge graph |
Base URL: http://localhost:4318
| Endpoint | Method | Description |
|---|---|---|
/v1/recall | POST | Quick semantic search |
/v1/store | POST | Store a new memory |
/v1/capture | POST | Store multiple structured memories |
/v1/pattern | POST | Store a structured workflow pattern |
/v1/case | POST | Store a structured problem-solution case |
/v1/promote | POST | Promote evidence into durable memory |
/v1/conflicts | GET | List or inspect promotion conflict candidates |
/v1/conflicts/audit | GET | Summarize stale/escalated conflict priorities |
/v1/conflicts/escalate | POST | Preview or apply conflict escalation metadata |
/v1/conflicts/resolve | POST | Resolve a stored conflict candidate (keep / accept / merge) |
/v1/checkpoint | POST | Store the current work checkpoint |
/v1/workflow-observe | POST | Store a workflow observation outside durable memory |
/v1/checkpoint/latest | GET | Fetch the latest checkpoint by session or scope |
/v1/workflow-health | GET | Inspect workflow health or return a degraded-workflow dashboard |
/v1/workflow-evidence | GET | Build a workflow evidence pack from recent issue observations |
/v1/resume | POST | Compose startup context for a fresh window |
/v1/search | POST | Advanced search with full metadata |
/v1/stats | GET | Memory statistics |
/v1/lint | GET | Memory quality lint report |
/v1/health | GET | Health check |
Full documentation: docs/api-reference.md
# Search & explore
bun run src/cli.ts search "your query"
bun run src/cli.ts explain "your query" --profile debug
bun run src/cli.ts distill "topic" --profile writing
bun run src/cli.ts stats
# Workflow observation
bun run src/cli.ts workflow-observe resume_context "Fresh window skipped continuity recovery." --outcome missed --scope project:recallnest
bun run src/cli.ts workflow-health resume_context --scope project:recallnest
bun run src/cli.ts workflow-evidence checkpoint_session --scope project:recallnest
# Conflict management
bun run src/cli.ts conflicts list
bun run src/cli.ts conflicts list --attention resolved
bun run src/cli.ts conflicts list --group-by cluster --attention resolved
bun run src/cli.ts conflicts audit
bun run src/cli.ts conflicts audit --export --format md
bun run src/cli.ts conflicts escalate --attention stale
bun run src/cli.ts conflicts show af70545a
bun run src/cli.ts conflicts resolve af70545a --keep-existing
bun run src/cli.ts conflicts resolve af70545a --merge
bun run src/cli.ts conflicts resolve --all --keep-existing --status open
# Memory health & visualization
bun run src/cli.ts lint # memory quality report
bun run src/cli.ts lint --scope project:myapp # lint a specific scope
bun run src/cli.ts graph --open # export & open knowledge graph
bun run src/cli.ts graph --max-nodes 50 # smaller graph
# Ingestion & diagnostics
bun run src/cli.ts ingest --source all
bun run src/cli.ts doctor
Multilingual Support
RecallNest works out of the box with English. For multilingual memory (Chinese, Japanese, Thai, and 20+ more), install babel-memory with the language packs you need:
# Chinese
npm install babel-memory jieba-wasm
# Japanese
npm install babel-memory @sglkc/kuromoji
# Thai
npm install babel-memory wordcut
# European languages (German, French, Spanish, Russian, etc.)
npm install babel-memory snowball-stemmers
# Multiple languages at once
npm install babel-memory jieba-wasm @sglkc/kuromoji snowball-stemmers
RecallNest auto-detects babel-memory at startup — no configuration needed. Without babel-memory, RecallNest still works perfectly with standard BM25 text search.
Project Status & Roadmap
RecallNest is actively maintained. All major architecture phases are complete — see the full Roadmap for current priorities and future plans.
Relationship to memory-lancedb-pro
RecallNest started as a fork of memory-lancedb-pro and shares its core ideas around hybrid retrieval, decay modeling, and memory-as-engineering-system. The key difference:
- memory-lancedb-pro is an OpenClaw plugin — it adds long-term memory to a single OpenClaw agent.
- RecallNest is a standalone memory layer — it serves Claude Code, Codex, and Gemini CLI simultaneously through MCP + HTTP API, with session continuity, structured assets, and conflict management built in.
Credit
| Source | Contribution |
|---|---|
| memory-lancedb-pro by @win4r | Fork base — hybrid retrieval, decay modeling, and memory architecture |
| Claude Code | Foundation and early project scaffolding |
| OpenAI Codex | Productization and MCP expansion |
Special thanks to Qin Chao (@win4r) and the CortexReach team for the foundational work.
Part of the 小试AI open-source AI workflow:
| Project | Description |
|---|---|
| babel-memory | Multilingual preprocessing for BM25 — 27+ languages, zero deps |
| cc-empire | Hooks/rules/methodology — the connective tissue of the whole ecosystem |
| telegram-ai-bridge | Telegram bots for Claude, Codex, and Gemini |
| tg-bridge-channel | Sister Telegram bridge using Claude Agent View background sessions |
| wechat-ai-bridge | Run Claude Code / Codex / Gemini in WeChat with session management |
| openclaw-tunnel | Docker ↔ host CLI bridge (maintenance mode — LanceDB test only) |
| digital-clone-skill | Build digital clones from corpus data |
| claude-code-studio | Multi-session collaboration platform for Claude Code |
| workflow-orchestrator | Natural-language pipeline orchestrator for Claude Code |
License
MIT