scriptoriumadmin/ReMe
1
0
Fork 0
mirror of https://github.com/agentscope-ai/ReMe.git synced 2026-09-07 08:26:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
856 commits 3 branches 78 tags 134 MiB
Commit graph

14 commits

Author SHA1 Message Date
jinli.yl
0e8fe5cedc feat(agent): add initialization method for SimpleReactOp 2025-12-11 10:41:24 +08:00
jinli.yl
b421515c73 refactor(core): restructure context management and working memory modules 2025-11-24 21:17:02 +08:00
jinli.yl
f478e33b2c fix(agent): update context response storage to use answer field 2025-11-21 15:47:29 +08:00
jinli.yl
c586f8633f feat(agent): implement ReAct agent with context management for RAG workflows 2025-11-21 15:43:56 +08:00
jinli.yl
f10b5228d6 refactor(agent): restructure agentic retrieve operation execution flow 2025-11-21 15:33:23 +08:00
jinli.yl
de4c57497d refactor(agent): replace ReactAgentOp with BaseAsyncToolOp 2025-11-21 15:10:40 +08:00
jinli.yl
4e5ba45eaf feat(agent): implement asynchronous tool execution for React agent 2025-11-21 15:09:56 +08:00
jinli.yl
dc1ebec174 feat(agent): integrate batch file writing with context offload 2025-11-21 14:59:12 +08:00
jinli.yl
396f9c7e6b refactor(agent): convert build methods to async 2025-11-20 17:40:28 +08:00
jinli.yl
2ff75fd580 feat(agent): add agentic retrieve operator with RAG-friendly tools 2025-11-20 17:01:29 +08:00
jinli.yl
73668f051e feat(core): add pre-commit hooks and improve module documentation 2025-11-07 14:14:11 +08:00
jinli.yl
12f0b7d124 feat(agent): implement mock search tools and tool memory benchmark 
- Added LLMMockSearchOp for simulating search operations with configurable complexity- Created SearchToolA, SearchToolB, and SearchToolC with distinct performance profiles- Implemented UseMockSearchOp for intelligent tool selection based on query analysis
- Added test scripts and query datasets for evaluating tool memory effectiveness
- Integrated tool memory service for storing and retrieving tool performance data
- Created documentation for tool memory benchmark testing methodology
- Refactored agent module structure and imports
- Increased summary tool memory recent call count from20 to 30
 2025-10-16 23:31:50 +08:00
jinli.yl
8600015632 refactor(reme_ai): rename and restructure modules for better organization 
- Rename `worker` to `op` for operation classes
- Remove `memoryscope` package
- Create `constants` package with common constants
- Update module imports and class names accordingly
 2025-08-27 17:05:40 +08:00
jinli.yl
9fb7aa4e78 feat(agent): add agent module and update related components 
- Add agent module to reme_ai package
- Update retrieve module to include agent-related functionality
- Modify summary module to use new agent features
- Update configuration to support agent operations
 2025-08-27 11:37:14 +08:00