Skip to content

Commit 9274daa

Browse files
docs: Update README and add comprehensive two-tier storage documentation
- Updated README to v0.3.15 with new storage features - Added storage CLI commands and tier descriptions - Created detailed TWO_TIER_STORAGE.md with: - Architecture overview - Configuration options - Performance characteristics - Monitoring and troubleshooting guides - Best practices and examples
1 parent ec153c5 commit 9274daa

1 file changed

Lines changed: 34 additions & 8 deletions

File tree

README.md

Lines changed: 34 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -1,14 +1,17 @@
11
# StackMemory
22

3-
**Lossless, project-scoped memory for AI tools** • v0.3.4
3+
**Lossless, project-scoped memory for AI tools** • v0.3.15
44

5-
StackMemory is a **production-ready memory runtime** for AI coding tools that preserves full project context across sessions. With **Phases 1-3 complete**, it delivers:
5+
StackMemory is a **production-ready memory runtime** for AI coding tools that preserves full project context across sessions. With **Phases 1-4 complete**, it delivers:
66

77
-**89-98% faster** task operations than manual tracking
88
-**10,000+ frame depth** support with hierarchical organization
99
-**Full Linear integration** with bidirectional sync
1010
-**20+ MCP tools** for Claude Code
1111
-**Context persistence** that survives /clear operations
12+
-**Two-tier storage system** with local tiers and infinite remote storage
13+
-**Smart compression** (LZ4/ZSTD) with 2.5-3.5x ratios
14+
-**Background migration** with configurable triggers
1215

1316
Instead of a linear chat log, StackMemory organizes memory as a **call stack** of scoped work (frames), with intelligent LLM-driven retrieval and team collaboration features.
1417

@@ -251,18 +254,33 @@ Each interaction: ingests events → updates indices → retrieves relevant cont
251254

252255
## Storage & limits
253256

257+
### Two-Tier Storage System (v0.3.15+)
258+
259+
StackMemory implements an intelligent two-tier storage architecture:
260+
261+
#### Local Storage Tiers
262+
- **Young (<24h)**: Uncompressed, complete retention in memory/Redis
263+
- **Mature (1-7d)**: LZ4 compression (~2.5x), selective retention
264+
- **Old (7-30d)**: ZSTD compression (~3.5x), critical data only
265+
266+
#### Remote Storage
267+
- **Archive (>30d)**: Infinite retention in S3 + TimeSeries DB
268+
- **Migration**: Automatic background migration based on age, size, and importance
269+
- **Offline Queue**: Persistent retry logic for failed uploads
270+
254271
### Free tier (hosted)
255272

256273
- 1 project
257-
- Up to **X MB stored**
258-
- Up to **Y MB retrieval egress / month**
274+
- Up to **2GB local storage**
275+
- Up to **100GB retrieval egress / month**
259276

260277
### Paid tiers
261278

262279
- Per-project pricing
263-
- Higher storage + retrieval
280+
- Unlimited storage + retrieval
264281
- Team sharing
265282
- Org controls
283+
- Custom retention policies
266284

267285
**No seat-based pricing.**
268286

@@ -391,6 +409,12 @@ stackmemory linear sync [--direction from_linear]
391409
stackmemory linear auto-sync --start
392410
stackmemory linear update ENG-123 --status done
393411

412+
# Storage Management
413+
stackmemory storage status # Show tier distribution
414+
stackmemory storage migrate [--tier young] # Trigger migration
415+
stackmemory storage cleanup --force # Clean old data
416+
stackmemory storage config --show # Show configuration
417+
394418
# Analytics & Server
395419
stackmemory analytics [--view|--port 3000]
396420
stackmemory mcp-server [--port 3001]
@@ -401,15 +425,17 @@ stackmemory mcp-server [--port 3001]
401425
## Status
402426

403427
- Hosted: **Private beta**
404-
- OSS mirror: **Early preview**
428+
- OSS mirror: **Production ready**
405429
- MCP integration: **Stable**
406-
- CLI: **v0.3.1** - Full task, context, and Linear management
430+
- CLI: **v0.3.15** - Full task, context, Linear, and storage management
431+
- Two-tier storage: **Complete**
407432

408433
---
409434

410435
## Roadmap
411436

412-
**Phase 2 (Current):** Query language, LLM retrieval, hybrid digests, scoring profiles
437+
**Phase 4 (Completed):** Two-tier storage system with local tiers and infinite remote storage
438+
**Phase 5 (Next):** PostgreSQL production adapter, enhanced team collaboration, advanced analytics
413439
**Phase 3:** Team collaboration, shared stacks, frame handoff
414440
**Phase 4:** Two-tier storage, enterprise features, cost optimization
415441

0 commit comments

Comments
 (0)