Rlm Python Packages

predict-rlm

Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs, and tools — the model handles its own control flow. Get fully interpretable trajectories and performance that scales directly with model improvements. Without context rot.

fast-rlm

A feature rich implementation of Recursive Language Models, with ACP integration, REPL tool support, structured IO, advanced visualization, logging tools.

aleph-rlm

Skill + MCP server to turn your agent into an RLM. Load context, iterate with search/code/think tools, converge on answers.

fleet-rlm

DSPy's Recursive Language Model (RLM) with Daytona Sandbox for secure cloud-based code execution

pyrlm-runtime

Minimal runtime for Recursive Language Models (RLMs) inspired by the MIT CSAIL paper "Recursive Language Models".

rlm-code

The Research Playground for the RLMSs and Coding Agents

agentic-codebase-navigator

Hexagonal architecture implementation of Recursive Language Models (RLM)

rlm-prometheus

Prometheus metrics collector and exporter for RLM (Reprise License Manager)

deeprecall

Recursive reasoning engine for AI agents and vector databases. Powered by MIT's RLM.

minrlm

A small Recursive Language Model (RLM) that lets any LLM run code on its context instead of stuffing it into the prompt. Includes RLM-Bench.

claude-memory-mcp

Persistent memory MCP server for Claude Code — never lose context again

enzu

Budgeted LLM runs with hard caps + typed outcomes + async job mode. Python/CLI/HTTP. OpenAI-compatible.

replm

Recursive Language Models — process arbitrarily long prompts by offloading context into a REPL and enabling symbolic recursion via sub-LLM calls

zigrlm

Zig runtime for Recursive Language Model workflows, inspired by alexzhang13/rlm