Skip to content
View manojbajaj95's full-sized avatar

Block or report manojbajaj95

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
manojbajaj95/README.md

Manoj Bajaj

Exploring agent-human interfaces and harness engineering.

Writing: mbajaj.me · for-agents.com

Harness engineering

EvoHarness - Continual Learning Harness ( Coming Soon )

Webcmd - Self-learning harness for browser automation

Knowledge cards - Reflection-based continual learning for agents

Benchmarking & Evals

Agent Learning Bench - Harbor benchmark to evaluate Agent learning capabilities

GA Bench - How coding agents generalize over long horizon knowledge work ( archived, supersed by MCP Atlas)

Past

Authsome - Credential broker for AI agents (stable, no longer actively developed)

Ruzo - Enterprise automated task execution (archived)

GTM Skills - GTM skills for AI-native teams

OpenArtifacts - Share agent artifacts with team ( sold )

Darin - Knowledge base for engineering teams ( archived )

Juxtapose - Multi-agent orchestration (archived)

Colab - Realtime collaboration canvas for agents and humans (merged with Darin, archived)

Open Knowledge Format Viewer - CLI to view markdown in the browser (merged with Darin, archived)

Pinned Loading

  1. agentrhq/authsome agentrhq/authsome Public

    Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.

    Python 90 9

  2. claude-gtm-plugin claude-gtm-plugin Public

    Skills for GTM teams

    HTML 100 30