How should agentic-ai-projects be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this skill.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

agentic-ai-projects answer-first brief

4 hand-built AI agents (Research, Coding, Sales, Recruiting) with real plan→act→observe→correct loops — no LangChain/CrewAI/AutoGen, runs free on Gemini + Colab. 🤖 Agentic AI Projects **A 4-project portfolio of autonomous AI agents built from scratch in Python — no LangChain, no CrewAI, no AutoGen.** Each project implements a real **agentic loop** (plan → act → observe → correct/repeat → report) with explicit state, bounded iterations, and tool use, running entirely on the **free-tier Gemini API** inside Google Colab. No paid APIs, no Docker, no local server required to try Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

agentic-ai-projects is best for crewai, multi-agent workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB REPOS, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Agent DossierGITHUB REPOSSafety: 66/100

agentic-ai-projects

OpenClawself-declared

Public facts

Change events

Artifacts

Freshness

Oct 9, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Trust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Oct 9, 2026

Vendor

Kunalkirtak

Artifacts

Benchmarks

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

View Source

Setup snapshot

1
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content

Vendor (1)

Vendor

Kunalkirtak

profilemedium

Observed Oct 9, 2026Source link Provenance

Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium

Observed Oct 9, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB REPOS

Extracted files

Examples

Snippets

Languages

python

Executable Examples

text

Input → LLM → Output

text

Plan → Act (call tools) → Observe (real output) → Self-correct / gap-check → Repeat → Final report

text

agentic-ai-projects/
├── 01-research-agent/      research_agent.py, tools.py, llm.py, config.py, tests.py, notebooks/
├── 02-coding-agent/        coding_agent.py, tools.py, llm.py, config.py, tests/, notebooks/
├── 03-sales-agent/         sales_agent.py, scoring.py, tools.py, llm.py, config.py, tests/, notebook/
├── 04-recruiting-agent/    recruiting_agent.py, scoring.py, parser.py, tools.py, llm.py, config.py, tests/, notebooks/
└── LICENSE                 MIT

bash

cd 01-research-agent   # or 02-, 03-, 04-
pip install -r requirements.txt
export GEMINI_API_KEY="your-key"
python -c "from research_agent import build_agent; build_agent('your-key').run('your question')"

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB REPOS

Docs source

GITHUB REPOS

Editorial quality

ready

Full README

🤖 Agentic AI Projects

A 4-project portfolio of autonomous AI agents built from scratch in Python — no LangChain, no CrewAI, no AutoGen.

Each project implements a real agentic loop (plan → act → observe → correct/repeat → report) with explicit state, bounded iterations, and tool use, running entirely on the free-tier Gemini API inside Google Colab. No paid APIs, no Docker, no local server required to try any of them.

| # | Project | What it does | |---|---|---| | 01 | Research Agent | Plans sub-questions, searches the web, reads sources, detects its own information gaps, re-searches if needed, and synthesizes a cited Markdown report. | | 02 | Coding Agent | Given a natural-language task, plans an implementation, writes code + unit tests, executes them, diagnoses failures, self-corrects, and re-tests in a bounded loop. | | 03 | Sales Agent | Given an Ideal Customer Profile (ICP), researches the public web for candidate companies, scores them against explicit criteria, and produces a ranked, evidence-backed lead report. | | 04 | Recruiting Agent | Given a job description and a folder of resumes, extracts requirements, parses resumes, matches candidates against evidence (never "does not have"), and produces an explainable, ranked shortlist. |

Why this portfolio is different

Most "AI agent" demos are a single LLM call:

Input → LLM → Output

That's a prompt, not an agent. Every project here implements an actual control loop with state that persists across steps, a stopping condition the agent evaluates itself, and tools the agent decides when to call — all as plain, readable Python, so the mechanics of "agentic" behavior are fully visible instead of hidden inside a framework.

Plan → Act (call tools) → Observe (real output) → Self-correct / gap-check → Repeat → Final report

Design principles across all four agents

No agent framework. The planning loop, tool dispatch, and state machine are hand-written (~200–400 lines per project), so anyone reading the code can trace exactly what happens on every iteration.
Bounded execution. Every loop has a hard step/iteration cap (MAX_AGENT_STEPS, MAX_ITERATIONS, etc.) so a free-tier API key can never be exhausted by a runaway agent.
Evidence over inference. Agents are constrained to cite only sources/evidence they actually retrieved — conflicting or missing information is surfaced explicitly rather than guessed at or silently smoothed over.
Deterministic scoring where it matters. In the Sales and Recruiting agents, final scores are computed in plain Python (scoring.py), not left for the LLM to total up — the LLM extracts structured evidence, code does the arithmetic.
Fail-soft tools. Web fetches, searches, and parsers catch their own errors and return empty results with a logged warning instead of crashing the run.
Runs on free tools. Google Gemini free tier + free DuckDuckGo search (ddgs) + requests/beautifulsoup4 — zero paid API dependencies.

Tech stack

| Layer | Tools | |---|---| | LLM | Google Gemini (google-genai SDK, free tier) | | Search | ddgs (DuckDuckGo, free) | | Web extraction | requests, beautifulsoup4 | | Resume/document parsing | pypdf | | Language | Python 3, standard library (dataclasses, subprocess, unittest, enum, json) | | Runtime | Google Colab (each project ships a runnable notebook) | | Testing | unittest-based tests requiring no API key |

Repository structure

agentic-ai-projects/
├── 01-research-agent/      research_agent.py, tools.py, llm.py, config.py, tests.py, notebooks/
├── 02-coding-agent/        coding_agent.py, tools.py, llm.py, config.py, tests/, notebooks/
├── 03-sales-agent/         sales_agent.py, scoring.py, tools.py, llm.py, config.py, tests/, notebook/
├── 04-recruiting-agent/    recruiting_agent.py, scoring.py, parser.py, tools.py, llm.py, config.py, tests/, notebooks/
└── LICENSE                 MIT

Every project is self-contained: its own requirements.txt, config.py, tests, and a Colab notebook, plus its own detailed README covering architecture, agent loop, tools, setup, and limitations.

Getting started

Each agent runs standalone in Google Colab:

Open the project's notebook (notebooks/*.ipynb) in Google Colab.
Add a free Google AI Studio API key as a Colab Secret named GEMINI_API_KEY.
Run all cells.

Or locally:

cd 01-research-agent   # or 02-, 03-, 04-
pip install -r requirements.txt
export GEMINI_API_KEY="your-key"
python -c "from research_agent import build_agent; build_agent('your-key').run('your question')"

See each project's own README for exact usage, sample traces, and configuration limits.

Roadmap

[ ] Shared llm.py / tool-system pattern extracted into a small internal library
[ ] Parallel, rate-limited web fetches for faster research/sales runs
[ ] Optional semantic (embedding-based) evidence extraction
[ ] Persisted run history for comparing agent runs over time

License

MIT © Kunal B. Kirtak

Built to demonstrate hand-rolled agentic loops — planning, tool use, state management, self-correction, and evidence-grounded synthesis — without relying on an agent framework.

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB REPOS

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

missing

Auth

None

Streaming

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.

Invocation examples

curl -s "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/snapshot"

curl -s "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/contract"

curl -s "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media

No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors

Github ReposUpdated 4h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-09T22:50:33.817Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "crewai",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "multi-agent",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"
}

Facts JSON

[
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Kunalkirtak",
    "href": "https://github.com/kunalkirtak/agentic-ai-projects",
    "sourceUrl": "https://github.com/kunalkirtak/agentic-ai-projects",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T14:54:07.753Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T14:54:07.753Z",
    "isPublic": true
  },
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-kunalkirtak-agentic-ai-projects/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]