Skip to content

Commit d0c42fa

Browse files
committed
Add a changelog
1 parent cfdf7db commit d0c42fa

File tree

2 files changed

+63
-26
lines changed

2 files changed

+63
-26
lines changed

CHANGELOG.md

Lines changed: 63 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,63 @@
1+
# Changelog
2+
3+
All notable changes to this project will be documented in this file.
4+
5+
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
6+
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
7+
8+
## [0.9.0] - 2025-06-13
9+
10+
*Changes from the initial release:**
11+
12+
### Architecture Evolution
13+
- **Working Memory (formerly Short-term Memory)**:
14+
- Renamed from "short-term memory" to "working memory" to better reflect its purpose
15+
- Enhanced with automatic promotion system that moves structured memories to long-term storage in background
16+
- Added support for arbitrary JSON data storage alongside memory structures
17+
- Improved automatic conversation summarization in working memory
18+
19+
20+
- **Working Memory -> Long-term Memory Promotion**:
21+
- Implemented seamless flow from working memory to long-term memory via background task processing
22+
- Agent only has to think about working memory, long-term memory is managed automatically (but can be managed manually, too)
23+
- Structured memories automatically promoted with vector embeddings and metadata indexing
24+
- Deduplication and compaction systems for long-term memory management
25+
- Background task worker system using Docket for reliable memory processing
26+
27+
### Client SDK and Tooling
28+
- Both working and long-term memory available as tools for LLM integration (LLM can choose to persist a long-term memory or search for long-term memories)
29+
- Memory-enriched prompt generation via `/v1/memory/prompt` endpoint
30+
- Unified search across both memory types with metadata filtering
31+
- Support for namespace isolation and session management
32+
33+
### Search and Retrieval
34+
- Vector-based similarity search using OpenAI embeddings
35+
- Rich filtering system by session, namespace, topics, entities, timestamps
36+
- Hybrid search combining semantic similarity with metadata filtering
37+
- RedisVL integration for high-performance vector operations with Redis
38+
39+
### Enhanced Memory Classification:
40+
- Semantic memories for facts and preferences
41+
- Episodic memories for time-bound events with event dates (requires a timeframe)
42+
- Message memories for conversation records
43+
- Automatic topic modeling and entity recognition either using BERTopic or a configured LLM
44+
- Rich metadata extraction and indexing
45+
46+
### Authentication and Security
47+
- OAuth2/JWT Bearer token authentication with JWKS validation
48+
- Multi-provider support (Auth0, AWS Cognito, Okta, Azure AD)
49+
- Role-based access control using JWT claims
50+
- Development mode with configurable auth bypass
51+
52+
### Operational Features
53+
- **Comprehensive CLI Interface**:
54+
- Commands for server management (`api`, `mcp`, `task-worker`)
55+
- Database operations (`rebuild-index`)
56+
- Background task scheduling and management
57+
- Health monitoring and diagnostics
58+
59+
60+
## [0.0.1]
61+
62+
### Initial Release - 2025-04-07
63+
- Initial release with basic short-term and long-term memory functionality

TASK_MEMORY.md

Lines changed: 0 additions & 26 deletions
This file was deleted.

0 commit comments

Comments
 (0)