Stop rebuilding memory and orchestration for every AI agent you build

Cognicore has released NEXUS, an open-source framework that provides a standardized memory, retry logic, and orchestration layer for AI agents, eliminating the need for developers to rebuild these components from scratch on every project. The framework, which can be installed with a single pip command, includes features such as compounding memory, an agent immune system against prompt injection, and replay/time travel capabilities. In ablation studies, the project found that minimal agent configurations outperformed larger multi-agent setups, with a two-agent Coder/Tester pipeline solving 19 out of 20 tasks at $0.014 per fix, while a five-agent pipeline solved 18 out of 20 at $0.009 per fix but with 9,642 additional tokens.

Your agent fails You restart it It fails at the exact same thing again Sound familiar The problem every AI team hits Every team building autonomous agents eventually rebuilds the same three things Memory so the agent remembers what failed last time Retry logic so it does not loop forever on the same broken approach Orchestration so multiple agents do not step on each other You build it It works You start the next project and build it again from scratch There is no standard layer for this Until now Introducing NEXUS One line install Works with any agent Gets smarter over time pip install cognicore env import cognicore as cc env = cc.make SafetyClassification Easy v1 agent = cc.AutoLearner cc.train agent=agent env=env episodes=30 score = cc.evaluate agent=agent env=env episodes=5 What makes it different Memory that compounds The more tasks NEXUS handles the better it gets text Week 1 0.05 per fix Week 4 0.02 per fix Week 8 0.01 per fix An agent with 6 months of memory on your codebase is fundamentally different from one starting cold Agent Immune System Protect any agent from prompt injection jailbreaks and token bombs python from cognicore.immune import NexusShield safe agent = NexusShield agent=your agent Replay and Time Travel Every decision event sourced Rewind any task to any step Branch and try a different strategy cognicore replay task abc123 cognicore branch task abc123 step 3 policy minimal 6 Enterprise Integrations Label a GitHub issue nexus NEXUS fixes it opens a PR automatically bash cognicore integrations setup Live Dashboard bash cognicore ui The research finding that surprised everyone I ran ablation studies comparing multi agent configurations Expected more specialized agents equals better results Actual minimal Coder Tester only 19 20 solved 0.014 full pipeline 5 agents 18 20 solved 0.009 review first ordering 18 20 solved 0.009 The Reviewer agent costs minus 1 solve rate and plus 9642 tokens More agents Worse performance More expensive An offline RL agent trained on 220 trajectories independently confirmed minimal policy wins 89 percent of task states For developers building AI agents Stop rebuilding memory from scratch on every project from cognicore import Memory ReflectionEngine mem = Memory ref = ReflectionEngine memory=mem action reason confidence = ref.suggest override null handling guard fix For ML researchers 38 built in environments across 6 domains 4 RL agent types with clean interfaces Ablation infrastructure with statistical rigor 460 plus trajectories exportable for offline RL SWE bench style evaluation built in CognitiveMemory with working episodic semantic and procedural layers from cognicore import Experiment exp = Experiment name=memory ablation env id=SafetyClassification v1 exp.add variant no memory cc.AutoLearner exp.add variant with memory cc.AutoLearner results = exp.run episodes=50 For CTOs and engineering leads Self hostable Open source core Apache 2.0 Token cost tracking built in Budget controls Full audit log GitHub Slack Linear integrations text Devin 500 month NEXUS 3 to 15 month Numbers 1700 plus downloads in first week 95 percent solve rate on SWE style benchmark 472 tests passing 62 built in environments 153 public API exports Zero required dependencies for core 6 enterprise integrations 460 plus trajectories stored for offline RL Try it in 2 minutes bash pip install cognicore env cognicore ui cognicore integrations setup python import cognicore as cc env = cc.make GridWorld v1 agent = cc.AutoLearner cc.train agent=agent env=env episodes=50 print cc.evaluate agent=agent env=env episodes=5 GitHub github com Kaushalt2004 cognicore my openenv PyPI pypi org project cognicore env Docs cognicore readthedocs io Open source Apache 2.0 Solo built Actively maintained Star the repo if this solves a problem you have hit before