2 dépôts
Awesome GitHub RepositoriesSequential Evaluation Engines
Mechanisms for running serial evaluation samples on persistent agent instances.
Distinct from Sequential Execution Engines: Distinct from general sequential execution: focuses on maintaining persistent agent state across multiple evaluation samples.
Explore 2 awesome GitHub repositories matching development tools & productivity · Sequential Evaluation Engines. Refine with filters or upvote what's useful.
Awesome Sequential Evaluation Engines GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- letta-ai/letta
letta-ai/letta
21,168Voir sur GitHubLetta is a framework for building, deploying, and managing autonomous AI agents that maintain persistent state across long-term interactions. It provides a comprehensive suite of primitives for defining agents with configurable personas, modular memory blocks, and tool-use capabilities, enabling them to retain user preferences and conversation history over extended sessions. The platform distinguishes itself through its advanced memory management and orchestration capabilities. It allows agents to autonomously update their own memory, perform retrieval-augmented generation, and coordinate com
Uses a single persistent agent instance across multiple samples to test memory accumulation and multi-turn conversation consistency.
Pythonaiai-agentsllm - evcxr/evcxr
evcxr/evcxr
6,436Voir sur GitHubEvalXR is an interactive Rust compiler that compiles code into dynamically loaded libraries for iterative evaluation without restarting the process. It serves as a Rust Jupyter kernel, a notebook runtime, and a REPL environment, all with state retention across evaluations. The project provides a stateful Rust evaluation engine that runs code snippets in isolated sandboxes while keeping functions and variables alive between executions. It supports cell-based execution, compiling Rust code into a shared library and loading it into the same process to preserve state, with an error-aware compilat
Evaluates Rust code snippets interactively while preserving state across evaluations for REPL and notebook environments.
Rust
